U-Net for Semantic Segmentation and LULC Mapping¶
Let's install the necessary libraries and then import them.
In [ ]:
!pip install geoai-py
!pip install ipysheet
!pip install rasterio
Collecting geoai-py
Downloading geoai_py-0.8.1-py2.py3-none-any.whl.metadata (6.7 kB)
Requirement already satisfied: albumentations in /usr/local/lib/python3.11/dist-packages (from geoai-py) (2.0.8)
Collecting buildingregulariser (from geoai-py)
Downloading buildingregulariser-0.2.2-py3-none-any.whl.metadata (6.9 kB)
Collecting contextily (from geoai-py)
Downloading contextily-1.6.2-py3-none-any.whl.metadata (2.9 kB)
Requirement already satisfied: geopandas in /usr/local/lib/python3.11/dist-packages (from geoai-py) (1.0.1)
Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.11/dist-packages (from geoai-py) (0.33.2)
Collecting jupyter-server-proxy (from geoai-py)
Downloading jupyter_server_proxy-4.4.0-py3-none-any.whl.metadata (8.7 kB)
Collecting leafmap (from geoai-py)
Downloading leafmap-0.48.6-py2.py3-none-any.whl.metadata (16 kB)
Collecting localtileserver (from geoai-py)
Downloading localtileserver-0.10.6-py3-none-any.whl.metadata (5.2 kB)
Collecting mapclassify (from geoai-py)
Downloading mapclassify-2.9.0-py3-none-any.whl.metadata (3.1 kB)
Collecting maplibre (from geoai-py)
Downloading maplibre-0.3.4-py3-none-any.whl.metadata (3.9 kB)
Requirement already satisfied: opencv-python-headless in /usr/local/lib/python3.11/dist-packages (from geoai-py) (4.11.0.86)
Collecting overturemaps (from geoai-py)
Downloading overturemaps-0.15.0-py3-none-any.whl.metadata (4.0 kB)
Collecting planetary-computer (from geoai-py)
Downloading planetary_computer-1.0.0-py3-none-any.whl.metadata (7.4 kB)
Collecting pystac-client (from geoai-py)
Downloading pystac_client-0.8.6-py3-none-any.whl.metadata (3.0 kB)
Collecting rasterio (from geoai-py)
Downloading rasterio-1.4.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (9.1 kB)
Collecting rioxarray (from geoai-py)
Downloading rioxarray-0.19.0-py3-none-any.whl.metadata (5.5 kB)
Requirement already satisfied: scikit-image in /usr/local/lib/python3.11/dist-packages (from geoai-py) (0.25.2)
Requirement already satisfied: scikit-learn in /usr/local/lib/python3.11/dist-packages (from geoai-py) (1.6.1)
Requirement already satisfied: torch in /usr/local/lib/python3.11/dist-packages (from geoai-py) (2.6.0+cu124)
Collecting torchgeo (from geoai-py)
Downloading torchgeo-0.7.1-py3-none-any.whl.metadata (18 kB)
Collecting torchinfo (from geoai-py)
Downloading torchinfo-1.8.0-py3-none-any.whl.metadata (21 kB)
Requirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (from geoai-py) (4.67.1)
Requirement already satisfied: transformers in /usr/local/lib/python3.11/dist-packages (from geoai-py) (4.53.0)
Requirement already satisfied: numpy>=1.24.4 in /usr/local/lib/python3.11/dist-packages (from albumentations->geoai-py) (2.0.2)
Requirement already satisfied: scipy>=1.10.0 in /usr/local/lib/python3.11/dist-packages (from albumentations->geoai-py) (1.15.3)
Requirement already satisfied: PyYAML in /usr/local/lib/python3.11/dist-packages (from albumentations->geoai-py) (6.0.2)
Requirement already satisfied: pydantic>=2.9.2 in /usr/local/lib/python3.11/dist-packages (from albumentations->geoai-py) (2.11.7)
Requirement already satisfied: albucore==0.0.24 in /usr/local/lib/python3.11/dist-packages (from albumentations->geoai-py) (0.0.24)
Requirement already satisfied: stringzilla>=3.10.4 in /usr/local/lib/python3.11/dist-packages (from albucore==0.0.24->albumentations->geoai-py) (3.12.5)
Requirement already satisfied: simsimd>=5.9.2 in /usr/local/lib/python3.11/dist-packages (from albucore==0.0.24->albumentations->geoai-py) (6.4.9)
Requirement already satisfied: pyogrio>=0.7.2 in /usr/local/lib/python3.11/dist-packages (from geopandas->geoai-py) (0.11.0)
Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from geopandas->geoai-py) (24.2)
Requirement already satisfied: pandas>=1.4.0 in /usr/local/lib/python3.11/dist-packages (from geopandas->geoai-py) (2.2.2)
Requirement already satisfied: pyproj>=3.3.0 in /usr/local/lib/python3.11/dist-packages (from geopandas->geoai-py) (3.7.1)
Requirement already satisfied: shapely>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from geopandas->geoai-py) (2.1.1)
Requirement already satisfied: geopy in /usr/local/lib/python3.11/dist-packages (from contextily->geoai-py) (2.4.1)
Requirement already satisfied: matplotlib in /usr/local/lib/python3.11/dist-packages (from contextily->geoai-py) (3.10.0)
Collecting mercantile (from contextily->geoai-py)
Downloading mercantile-1.2.1-py3-none-any.whl.metadata (4.8 kB)
Requirement already satisfied: pillow in /usr/local/lib/python3.11/dist-packages (from contextily->geoai-py) (11.2.1)
Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from contextily->geoai-py) (2.32.3)
Requirement already satisfied: joblib in /usr/local/lib/python3.11/dist-packages (from contextily->geoai-py) (1.5.1)
Requirement already satisfied: xyzservices in /usr/local/lib/python3.11/dist-packages (from contextily->geoai-py) (2025.4.0)
Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from huggingface_hub->geoai-py) (3.18.0)
Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub->geoai-py) (2025.3.2)
Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub->geoai-py) (4.14.0)
Requirement already satisfied: hf-xet<2.0.0,>=1.1.2 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub->geoai-py) (1.1.5)
Requirement already satisfied: aiohttp in /usr/local/lib/python3.11/dist-packages (from jupyter-server-proxy->geoai-py) (3.11.15)
Collecting jupyter-server>=1.24.0 (from jupyter-server-proxy->geoai-py)
Downloading jupyter_server-2.16.0-py3-none-any.whl.metadata (8.5 kB)
Collecting simpervisor>=1.0.0 (from jupyter-server-proxy->geoai-py)
Downloading simpervisor-1.0.0-py3-none-any.whl.metadata (4.3 kB)
Requirement already satisfied: tornado>=6.1.0 in /usr/local/lib/python3.11/dist-packages (from jupyter-server-proxy->geoai-py) (6.4.2)
Requirement already satisfied: traitlets>=5.1.0 in /usr/local/lib/python3.11/dist-packages (from jupyter-server-proxy->geoai-py) (5.7.1)
Collecting anywidget (from leafmap->geoai-py)
Downloading anywidget-0.9.18-py3-none-any.whl.metadata (8.9 kB)
Requirement already satisfied: bqplot in /usr/local/lib/python3.11/dist-packages (from leafmap->geoai-py) (0.12.45)
Requirement already satisfied: duckdb in /usr/local/lib/python3.11/dist-packages (from leafmap->geoai-py) (1.2.2)
Requirement already satisfied: folium in /usr/local/lib/python3.11/dist-packages (from leafmap->geoai-py) (0.19.7)
Requirement already satisfied: gdown in /usr/local/lib/python3.11/dist-packages (from leafmap->geoai-py) (5.2.0)
Collecting geojson (from leafmap->geoai-py)
Downloading geojson-3.2.0-py3-none-any.whl.metadata (16 kB)
Requirement already satisfied: ipyevents in /usr/local/lib/python3.11/dist-packages (from leafmap->geoai-py) (2.0.2)
Requirement already satisfied: ipyfilechooser in /usr/local/lib/python3.11/dist-packages (from leafmap->geoai-py) (0.6.0)
Requirement already satisfied: ipyleaflet in /usr/local/lib/python3.11/dist-packages (from leafmap->geoai-py) (0.20.0)
Collecting ipyvuetify (from leafmap->geoai-py)
Downloading ipyvuetify-1.11.3-py2.py3-none-any.whl.metadata (7.5 kB)
Requirement already satisfied: ipywidgets in /usr/local/lib/python3.11/dist-packages (from leafmap->geoai-py) (7.7.1)
Requirement already satisfied: plotly in /usr/local/lib/python3.11/dist-packages (from leafmap->geoai-py) (5.24.1)
Requirement already satisfied: python-box in /usr/local/lib/python3.11/dist-packages (from leafmap->geoai-py) (7.3.2)
Requirement already satisfied: scooby in /usr/local/lib/python3.11/dist-packages (from leafmap->geoai-py) (0.10.1)
Collecting whiteboxgui (from leafmap->geoai-py)
Downloading whiteboxgui-2.3.0-py2.py3-none-any.whl.metadata (5.7 kB)
Requirement already satisfied: click in /usr/local/lib/python3.11/dist-packages (from localtileserver->geoai-py) (8.2.1)
Requirement already satisfied: flask<4,>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from localtileserver->geoai-py) (3.1.1)
Collecting Flask-Caching (from localtileserver->geoai-py)
Downloading Flask_Caching-2.3.1-py3-none-any.whl.metadata (2.2 kB)
Collecting flask-cors (from localtileserver->geoai-py)
Downloading flask_cors-6.0.1-py3-none-any.whl.metadata (5.3 kB)
Collecting flask-restx>=1.3.0 (from localtileserver->geoai-py)
Downloading flask_restx-1.3.0-py2.py3-none-any.whl.metadata (9.3 kB)
Collecting rio-tiler (from localtileserver->geoai-py)
Downloading rio_tiler-7.8.1-py3-none-any.whl.metadata (12 kB)
Collecting rio-cogeo (from localtileserver->geoai-py)
Downloading rio_cogeo-5.4.2-py3-none-any.whl.metadata (4.7 kB)
Collecting server-thread (from localtileserver->geoai-py)
Downloading server_thread-0.3.0-py3-none-any.whl.metadata (5.3 kB)
Requirement already satisfied: werkzeug in /usr/local/lib/python3.11/dist-packages (from localtileserver->geoai-py) (3.1.3)
Requirement already satisfied: networkx>=3.2 in /usr/local/lib/python3.11/dist-packages (from mapclassify->geoai-py) (3.5)
Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn->geoai-py) (3.6.0)
Requirement already satisfied: branca in /usr/local/lib/python3.11/dist-packages (from maplibre->geoai-py) (0.8.1)
Collecting eval-type-backport (from maplibre->geoai-py)
Downloading eval_type_backport-0.2.2-py3-none-any.whl.metadata (2.2 kB)
Requirement already satisfied: jinja2>=3.1.6 in /usr/local/lib/python3.11/dist-packages (from maplibre->geoai-py) (3.1.6)
Requirement already satisfied: pyarrow>=15.0.2 in /usr/local/lib/python3.11/dist-packages (from overturemaps->geoai-py) (18.1.0)
Collecting pystac>=1.0.0 (from planetary-computer->geoai-py)
Downloading pystac-1.13.0-py3-none-any.whl.metadata (4.7 kB)
Requirement already satisfied: pytz>=2020.5 in /usr/local/lib/python3.11/dist-packages (from planetary-computer->geoai-py) (2025.2)
Collecting python-dotenv (from planetary-computer->geoai-py)
Downloading python_dotenv-1.1.1-py3-none-any.whl.metadata (24 kB)
Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pystac-client->geoai-py) (2.9.0.post0)
Collecting affine (from rasterio->geoai-py)
Downloading affine-2.4.0-py3-none-any.whl.metadata (4.0 kB)
Requirement already satisfied: attrs in /usr/local/lib/python3.11/dist-packages (from rasterio->geoai-py) (25.3.0)
Requirement already satisfied: certifi in /usr/local/lib/python3.11/dist-packages (from rasterio->geoai-py) (2025.6.15)
Collecting cligj>=0.5 (from rasterio->geoai-py)
Downloading cligj-0.7.2-py3-none-any.whl.metadata (5.0 kB)
Collecting click-plugins (from rasterio->geoai-py)
Downloading click_plugins-1.1.1.2-py2.py3-none-any.whl.metadata (6.5 kB)
Requirement already satisfied: pyparsing in /usr/local/lib/python3.11/dist-packages (from rasterio->geoai-py) (3.2.3)
Requirement already satisfied: xarray>=2024.7.0 in /usr/local/lib/python3.11/dist-packages (from rioxarray->geoai-py) (2025.3.1)
Requirement already satisfied: imageio!=2.35.0,>=2.33 in /usr/local/lib/python3.11/dist-packages (from scikit-image->geoai-py) (2.37.0)
Requirement already satisfied: tifffile>=2022.8.12 in /usr/local/lib/python3.11/dist-packages (from scikit-image->geoai-py) (2025.6.11)
Requirement already satisfied: lazy-loader>=0.4 in /usr/local/lib/python3.11/dist-packages (from scikit-image->geoai-py) (0.4)
Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch->geoai-py)
Downloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-cuda-runtime-cu12==12.4.127 (from torch->geoai-py)
Downloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-cuda-cupti-cu12==12.4.127 (from torch->geoai-py)
Downloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)
Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch->geoai-py)
Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)
Collecting nvidia-cublas-cu12==12.4.5.8 (from torch->geoai-py)
Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-cufft-cu12==11.2.1.3 (from torch->geoai-py)
Downloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-curand-cu12==10.3.5.147 (from torch->geoai-py)
Downloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-cusolver-cu12==11.6.1.9 (from torch->geoai-py)
Downloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)
Collecting nvidia-cusparse-cu12==12.3.1.170 (from torch->geoai-py)
Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)
Requirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /usr/local/lib/python3.11/dist-packages (from torch->geoai-py) (0.6.2)
Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch->geoai-py) (2.21.5)
Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->geoai-py) (12.4.127)
Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch->geoai-py)
Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
Requirement already satisfied: triton==3.2.0 in /usr/local/lib/python3.11/dist-packages (from torch->geoai-py) (3.2.0)
Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch->geoai-py) (1.13.1)
Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch->geoai-py) (1.3.0)
Requirement already satisfied: einops>=0.3 in /usr/local/lib/python3.11/dist-packages (from torchgeo->geoai-py) (0.8.1)
Collecting fiona>=1.8.22 (from torchgeo->geoai-py)
Downloading fiona-1.10.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (56 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 56.6/56.6 kB 4.7 MB/s eta 0:00:00
Collecting kornia>=0.7.4 (from torchgeo->geoai-py)
Downloading kornia-0.8.1-py2.py3-none-any.whl.metadata (17 kB)
Collecting lightly!=1.4.26,>=1.4.5 (from torchgeo->geoai-py)
Downloading lightly-1.5.21-py3-none-any.whl.metadata (37 kB)
Collecting lightning!=2.3.*,!=2.5.0,>=2 (from lightning[pytorch-extra]!=2.3.*,!=2.5.0,>=2->torchgeo->geoai-py)
Downloading lightning-2.5.2-py3-none-any.whl.metadata (38 kB)
Collecting rtree>=1.0.1 (from torchgeo->geoai-py)
Downloading rtree-1.4.0-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.metadata (2.1 kB)
Collecting segmentation-models-pytorch>=0.5 (from torchgeo->geoai-py)
Downloading segmentation_models_pytorch-0.5.0-py3-none-any.whl.metadata (17 kB)
Requirement already satisfied: timm>=0.9.2 in /usr/local/lib/python3.11/dist-packages (from torchgeo->geoai-py) (1.0.16)
Collecting torchmetrics>=1.2 (from torchgeo->geoai-py)
Downloading torchmetrics-1.7.4-py3-none-any.whl.metadata (21 kB)
Requirement already satisfied: torchvision>=0.15.1 in /usr/local/lib/python3.11/dist-packages (from torchgeo->geoai-py) (0.21.0+cu124)
Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.11/dist-packages (from transformers->geoai-py) (2024.11.6)
Requirement already satisfied: tokenizers<0.22,>=0.21 in /usr/local/lib/python3.11/dist-packages (from transformers->geoai-py) (0.21.2)
Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.11/dist-packages (from transformers->geoai-py) (0.5.3)
Requirement already satisfied: blinker>=1.9.0 in /usr/local/lib/python3.11/dist-packages (from flask<4,>=2.0.0->localtileserver->geoai-py) (1.9.0)
Requirement already satisfied: itsdangerous>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from flask<4,>=2.0.0->localtileserver->geoai-py) (2.2.0)
Requirement already satisfied: markupsafe>=2.1.1 in /usr/local/lib/python3.11/dist-packages (from flask<4,>=2.0.0->localtileserver->geoai-py) (3.0.2)
Collecting aniso8601>=0.82 (from flask-restx>=1.3.0->localtileserver->geoai-py)
Downloading aniso8601-10.0.1-py2.py3-none-any.whl.metadata (23 kB)
Requirement already satisfied: jsonschema in /usr/local/lib/python3.11/dist-packages (from flask-restx>=1.3.0->localtileserver->geoai-py) (4.24.0)
Requirement already satisfied: importlib-resources in /usr/local/lib/python3.11/dist-packages (from flask-restx>=1.3.0->localtileserver->geoai-py) (6.5.2)
Requirement already satisfied: anyio>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (4.9.0)
Requirement already satisfied: argon2-cffi>=21.1 in /usr/local/lib/python3.11/dist-packages (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (25.1.0)
Collecting jupyter-client>=7.4.4 (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py)
Downloading jupyter_client-8.6.3-py3-none-any.whl.metadata (8.3 kB)
Requirement already satisfied: jupyter-core!=5.0.*,>=4.12 in /usr/local/lib/python3.11/dist-packages (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (5.8.1)
Collecting jupyter-events>=0.11.0 (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py)
Downloading jupyter_events-0.12.0-py3-none-any.whl.metadata (5.8 kB)
Collecting jupyter-server-terminals>=0.4.4 (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py)
Downloading jupyter_server_terminals-0.5.3-py3-none-any.whl.metadata (5.6 kB)
Requirement already satisfied: nbconvert>=6.4.4 in /usr/local/lib/python3.11/dist-packages (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (7.16.6)
Requirement already satisfied: nbformat>=5.3.0 in /usr/local/lib/python3.11/dist-packages (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (5.10.4)
Collecting overrides>=5.0 (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py)
Downloading overrides-7.7.0-py3-none-any.whl.metadata (5.8 kB)
Requirement already satisfied: prometheus-client>=0.9 in /usr/local/lib/python3.11/dist-packages (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (0.22.1)
Requirement already satisfied: pyzmq>=24 in /usr/local/lib/python3.11/dist-packages (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (24.0.1)
Requirement already satisfied: send2trash>=1.8.2 in /usr/local/lib/python3.11/dist-packages (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (1.8.3)
Requirement already satisfied: terminado>=0.8.3 in /usr/local/lib/python3.11/dist-packages (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (0.18.1)
Requirement already satisfied: websocket-client>=1.7 in /usr/local/lib/python3.11/dist-packages (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (1.8.0)
Collecting kornia_rs>=0.1.9 (from kornia>=0.7.4->torchgeo->geoai-py)
Downloading kornia_rs-0.1.9-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (11 kB)
Collecting hydra-core>=1.0.0 (from lightly!=1.4.26,>=1.4.5->torchgeo->geoai-py)
Downloading hydra_core-1.3.2-py3-none-any.whl.metadata (5.5 kB)
Collecting lightly_utils~=0.0.0 (from lightly!=1.4.26,>=1.4.5->torchgeo->geoai-py)
Downloading lightly_utils-0.0.2-py3-none-any.whl.metadata (1.4 kB)
Requirement already satisfied: six>=1.10 in /usr/local/lib/python3.11/dist-packages (from lightly!=1.4.26,>=1.4.5->torchgeo->geoai-py) (1.17.0)
Collecting pytorch_lightning>=1.0.4 (from lightly!=1.4.26,>=1.4.5->torchgeo->geoai-py)
Downloading pytorch_lightning-2.5.2-py3-none-any.whl.metadata (21 kB)
Requirement already satisfied: urllib3>=1.25.3 in /usr/local/lib/python3.11/dist-packages (from lightly!=1.4.26,>=1.4.5->torchgeo->geoai-py) (2.4.0)
Collecting aenum>=3.1.11 (from lightly!=1.4.26,>=1.4.5->torchgeo->geoai-py)
Downloading aenum-3.1.16-py3-none-any.whl.metadata (3.8 kB)
Collecting lightning-utilities<2.0,>=0.10.0 (from lightning!=2.3.*,!=2.5.0,>=2->lightning[pytorch-extra]!=2.3.*,!=2.5.0,>=2->torchgeo->geoai-py)
Downloading lightning_utilities-0.14.3-py3-none-any.whl.metadata (5.6 kB)
Collecting bitsandbytes<1.0,>=0.45.2 (from lightning[pytorch-extra]!=2.3.*,!=2.5.0,>=2->torchgeo->geoai-py)
Downloading bitsandbytes-0.46.1-py3-none-manylinux_2_24_x86_64.whl.metadata (10 kB)
Collecting jsonargparse<5.0,>=4.39.0 (from jsonargparse[jsonnet,signatures]<5.0,>=4.39.0; extra == "pytorch-extra"->lightning[pytorch-extra]!=2.3.*,!=2.5.0,>=2->torchgeo->geoai-py)
Downloading jsonargparse-4.40.0-py3-none-any.whl.metadata (13 kB)
Requirement already satisfied: omegaconf<3.0,>=2.2.3 in /usr/local/lib/python3.11/dist-packages (from lightning[pytorch-extra]!=2.3.*,!=2.5.0,>=2->torchgeo->geoai-py) (2.3.0)
Requirement already satisfied: rich<15.0,>=12.3.0 in /usr/local/lib/python3.11/dist-packages (from lightning[pytorch-extra]!=2.3.*,!=2.5.0,>=2->torchgeo->geoai-py) (13.9.4)
Collecting tensorboardX<3.0,>=2.2 (from lightning[pytorch-extra]!=2.3.*,!=2.5.0,>=2->torchgeo->geoai-py)
Downloading tensorboardx-2.6.4-py3-none-any.whl.metadata (6.2 kB)
Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->contextily->geoai-py) (1.3.2)
Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib->contextily->geoai-py) (0.12.1)
Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib->contextily->geoai-py) (4.58.4)
Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->contextily->geoai-py) (1.4.8)
Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas>=1.4.0->geopandas->geoai-py) (2025.2)
Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.11/dist-packages (from pydantic>=2.9.2->albumentations->geoai-py) (0.7.0)
Requirement already satisfied: pydantic-core==2.33.2 in /usr/local/lib/python3.11/dist-packages (from pydantic>=2.9.2->albumentations->geoai-py) (2.33.2)
Requirement already satisfied: typing-inspection>=0.4.0 in /usr/local/lib/python3.11/dist-packages (from pydantic>=2.9.2->albumentations->geoai-py) (0.4.1)
Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->contextily->geoai-py) (3.4.2)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests->contextily->geoai-py) (3.10)
Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->jupyter-server-proxy->geoai-py) (2.6.1)
Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/dist-packages (from aiohttp->jupyter-server-proxy->geoai-py) (1.3.2)
Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from aiohttp->jupyter-server-proxy->geoai-py) (1.7.0)
Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp->jupyter-server-proxy->geoai-py) (6.6.3)
Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->jupyter-server-proxy->geoai-py) (0.3.2)
Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->jupyter-server-proxy->geoai-py) (1.20.1)
Collecting psygnal>=0.8.1 (from anywidget->leafmap->geoai-py)
Downloading psygnal-0.14.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (6.0 kB)
Requirement already satisfied: ipykernel>=4.5.1 in /usr/local/lib/python3.11/dist-packages (from ipywidgets->leafmap->geoai-py) (6.17.1)
Requirement already satisfied: ipython-genutils~=0.2.0 in /usr/local/lib/python3.11/dist-packages (from ipywidgets->leafmap->geoai-py) (0.2.0)
Requirement already satisfied: widgetsnbextension~=3.6.0 in /usr/local/lib/python3.11/dist-packages (from ipywidgets->leafmap->geoai-py) (3.6.10)
Requirement already satisfied: ipython>=4.0.0 in /usr/local/lib/python3.11/dist-packages (from ipywidgets->leafmap->geoai-py) (7.34.0)
Requirement already satisfied: jupyterlab-widgets>=1.0.0 in /usr/local/lib/python3.11/dist-packages (from ipywidgets->leafmap->geoai-py) (3.0.15)
Requirement already satisfied: traittypes>=0.0.6 in /usr/local/lib/python3.11/dist-packages (from bqplot->leafmap->geoai-py) (0.2.1)
Collecting cachelib>=0.9.0 (from Flask-Caching->localtileserver->geoai-py)
Downloading cachelib-0.13.0-py3-none-any.whl.metadata (2.0 kB)
Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.11/dist-packages (from gdown->leafmap->geoai-py) (4.13.4)
Requirement already satisfied: geographiclib<3,>=1.52 in /usr/local/lib/python3.11/dist-packages (from geopy->contextily->geoai-py) (2.0)
Requirement already satisfied: jupyter-leaflet<0.21,>=0.20 in /usr/local/lib/python3.11/dist-packages (from ipyleaflet->leafmap->geoai-py) (0.20.0)
Collecting ipyvue<2,>=1.7 (from ipyvuetify->leafmap->geoai-py)
Downloading ipyvue-1.11.2-py2.py3-none-any.whl.metadata (1.1 kB)
Requirement already satisfied: tenacity>=6.2.0 in /usr/local/lib/python3.11/dist-packages (from plotly->leafmap->geoai-py) (8.5.0)
Collecting morecantile<7.0,>=5.0 (from rio-cogeo->localtileserver->geoai-py)
Downloading morecantile-6.2.0-py3-none-any.whl.metadata (7.3 kB)
Requirement already satisfied: cachetools in /usr/local/lib/python3.11/dist-packages (from rio-tiler->localtileserver->geoai-py) (5.5.2)
Collecting color-operations (from rio-tiler->localtileserver->geoai-py)
Downloading color_operations-0.2.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.3 kB)
Requirement already satisfied: httpx in /usr/local/lib/python3.11/dist-packages (from rio-tiler->localtileserver->geoai-py) (0.28.1)
Requirement already satisfied: numexpr in /usr/local/lib/python3.11/dist-packages (from rio-tiler->localtileserver->geoai-py) (2.11.0)
Requirement already satisfied: uvicorn in /usr/local/lib/python3.11/dist-packages (from server-thread->localtileserver->geoai-py) (0.35.0)
Requirement already satisfied: ipytree in /usr/local/lib/python3.11/dist-packages (from whiteboxgui->leafmap->geoai-py) (0.2.2)
Collecting whitebox (from whiteboxgui->leafmap->geoai-py)
Downloading whitebox-2.3.6-py2.py3-none-any.whl.metadata (11 kB)
Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.11/dist-packages (from anyio>=3.1.0->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (1.3.1)
Requirement already satisfied: argon2-cffi-bindings in /usr/local/lib/python3.11/dist-packages (from argon2-cffi>=21.1->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (21.2.0)
Requirement already satisfied: antlr4-python3-runtime==4.9.* in /usr/local/lib/python3.11/dist-packages (from hydra-core>=1.0.0->lightly!=1.4.26,>=1.4.5->torchgeo->geoai-py) (4.9.3)
Requirement already satisfied: debugpy>=1.0 in /usr/local/lib/python3.11/dist-packages (from ipykernel>=4.5.1->ipywidgets->leafmap->geoai-py) (1.8.0)
Requirement already satisfied: matplotlib-inline>=0.1 in /usr/local/lib/python3.11/dist-packages (from ipykernel>=4.5.1->ipywidgets->leafmap->geoai-py) (0.1.7)
Requirement already satisfied: nest-asyncio in /usr/local/lib/python3.11/dist-packages (from ipykernel>=4.5.1->ipywidgets->leafmap->geoai-py) (1.6.0)
Requirement already satisfied: psutil in /usr/local/lib/python3.11/dist-packages (from ipykernel>=4.5.1->ipywidgets->leafmap->geoai-py) (5.9.5)
Requirement already satisfied: setuptools>=18.5 in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets->leafmap->geoai-py) (75.2.0)
Collecting jedi>=0.16 (from ipython>=4.0.0->ipywidgets->leafmap->geoai-py)
Downloading jedi-0.19.2-py2.py3-none-any.whl.metadata (22 kB)
Requirement already satisfied: decorator in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets->leafmap->geoai-py) (4.4.2)
Requirement already satisfied: pickleshare in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets->leafmap->geoai-py) (0.7.5)
Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets->leafmap->geoai-py) (3.0.51)
Requirement already satisfied: pygments in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets->leafmap->geoai-py) (2.19.2)
Requirement already satisfied: backcall in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets->leafmap->geoai-py) (0.2.0)
Requirement already satisfied: pexpect>4.3 in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets->leafmap->geoai-py) (4.9.0)
Requirement already satisfied: docstring-parser>=0.15 in /usr/local/lib/python3.11/dist-packages (from jsonargparse[jsonnet,signatures]<5.0,>=4.39.0; extra == "pytorch-extra"->lightning[pytorch-extra]!=2.3.*,!=2.5.0,>=2->torchgeo->geoai-py) (0.16)
Collecting typeshed-client>=2.3.0 (from jsonargparse[jsonnet,signatures]<5.0,>=4.39.0; extra == "pytorch-extra"->lightning[pytorch-extra]!=2.3.*,!=2.5.0,>=2->torchgeo->geoai-py)
Downloading typeshed_client-2.7.0-py3-none-any.whl.metadata (7.9 kB)
Collecting jsonnet>=0.21.0 (from jsonargparse[jsonnet,signatures]<5.0,>=4.39.0; extra == "pytorch-extra"->lightning[pytorch-extra]!=2.3.*,!=2.5.0,>=2->torchgeo->geoai-py)
Downloading jsonnet-0.21.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (449 bytes)
Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.11/dist-packages (from jsonschema->flask-restx>=1.3.0->localtileserver->geoai-py) (2025.4.1)
Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.11/dist-packages (from jsonschema->flask-restx>=1.3.0->localtileserver->geoai-py) (0.36.2)
Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.11/dist-packages (from jsonschema->flask-restx>=1.3.0->localtileserver->geoai-py) (0.26.0)
Requirement already satisfied: platformdirs>=2.5 in /usr/local/lib/python3.11/dist-packages (from jupyter-core!=5.0.*,>=4.12->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (4.3.8)
Collecting python-json-logger>=2.0.4 (from jupyter-events>=0.11.0->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py)
Downloading python_json_logger-3.3.0-py3-none-any.whl.metadata (4.0 kB)
Collecting rfc3339-validator (from jupyter-events>=0.11.0->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py)
Downloading rfc3339_validator-0.1.4-py2.py3-none-any.whl.metadata (1.5 kB)
Collecting rfc3986-validator>=0.1.1 (from jupyter-events>=0.11.0->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py)
Downloading rfc3986_validator-0.1.1-py2.py3-none-any.whl.metadata (1.7 kB)
Requirement already satisfied: bleach!=5.0.0 in /usr/local/lib/python3.11/dist-packages (from bleach[css]!=5.0.0->nbconvert>=6.4.4->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (6.2.0)
Requirement already satisfied: defusedxml in /usr/local/lib/python3.11/dist-packages (from nbconvert>=6.4.4->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (0.7.1)
Requirement already satisfied: jupyterlab-pygments in /usr/local/lib/python3.11/dist-packages (from nbconvert>=6.4.4->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (0.3.0)
Requirement already satisfied: mistune<4,>=2.0.3 in /usr/local/lib/python3.11/dist-packages (from nbconvert>=6.4.4->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (3.1.3)
Requirement already satisfied: nbclient>=0.5.0 in /usr/local/lib/python3.11/dist-packages (from nbconvert>=6.4.4->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (0.10.2)
Requirement already satisfied: pandocfilters>=1.4.1 in /usr/local/lib/python3.11/dist-packages (from nbconvert>=6.4.4->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (1.5.1)
Requirement already satisfied: fastjsonschema>=2.15 in /usr/local/lib/python3.11/dist-packages (from nbformat>=5.3.0->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (2.21.1)
Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from rich<15.0,>=12.3.0->lightning[pytorch-extra]!=2.3.*,!=2.5.0,>=2->torchgeo->geoai-py) (3.0.0)
Requirement already satisfied: protobuf>=3.20 in /usr/local/lib/python3.11/dist-packages (from tensorboardX<3.0,>=2.2->lightning[pytorch-extra]!=2.3.*,!=2.5.0,>=2->torchgeo->geoai-py) (5.29.5)
Requirement already satisfied: ptyprocess in /usr/local/lib/python3.11/dist-packages (from terminado>=0.8.3->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (0.7.0)
Requirement already satisfied: notebook>=4.4.1 in /usr/local/lib/python3.11/dist-packages (from widgetsnbextension~=3.6.0->ipywidgets->leafmap->geoai-py) (6.5.7)
Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.11/dist-packages (from beautifulsoup4->gdown->leafmap->geoai-py) (2.7)
Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.11/dist-packages (from httpx->rio-tiler->localtileserver->geoai-py) (1.0.9)
Requirement already satisfied: h11>=0.16 in /usr/local/lib/python3.11/dist-packages (from httpcore==1.*->httpx->rio-tiler->localtileserver->geoai-py) (0.16.0)
Requirement already satisfied: PySocks!=1.5.7,>=1.5.6 in /usr/local/lib/python3.11/dist-packages (from requests[socks]->gdown->leafmap->geoai-py) (1.7.1)
Requirement already satisfied: webencodings in /usr/local/lib/python3.11/dist-packages (from bleach!=5.0.0->bleach[css]!=5.0.0->nbconvert>=6.4.4->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (0.5.1)
Requirement already satisfied: tinycss2<1.5,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from bleach[css]!=5.0.0->nbconvert>=6.4.4->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (1.4.0)
Requirement already satisfied: parso<0.9.0,>=0.8.4 in /usr/local/lib/python3.11/dist-packages (from jedi>=0.16->ipython>=4.0.0->ipywidgets->leafmap->geoai-py) (0.8.4)
Collecting fqdn (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py)
Downloading fqdn-1.5.1-py3-none-any.whl.metadata (1.4 kB)
Collecting isoduration (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py)
Downloading isoduration-20.11.0-py3-none-any.whl.metadata (5.7 kB)
Requirement already satisfied: jsonpointer>1.13 in /usr/local/lib/python3.11/dist-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (3.0.0)
Collecting uri-template (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py)
Downloading uri_template-1.3.0-py3-none-any.whl.metadata (8.8 kB)
Requirement already satisfied: webcolors>=24.6.0 in /usr/local/lib/python3.11/dist-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (24.11.1)
Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.11/dist-packages (from markdown-it-py>=2.2.0->rich<15.0,>=12.3.0->lightning[pytorch-extra]!=2.3.*,!=2.5.0,>=2->torchgeo->geoai-py) (0.1.2)
Collecting jupyter-client>=7.4.4 (from jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py)
Downloading jupyter_client-7.4.9-py3-none-any.whl.metadata (8.5 kB)
Requirement already satisfied: nbclassic>=0.4.7 in /usr/local/lib/python3.11/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->leafmap->geoai-py) (1.3.1)
Requirement already satisfied: entrypoints in /usr/local/lib/python3.11/dist-packages (from jupyter-client>=7.4.4->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (0.4)
Requirement already satisfied: wcwidth in /usr/local/lib/python3.11/dist-packages (from prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0->ipython>=4.0.0->ipywidgets->leafmap->geoai-py) (0.2.13)
Requirement already satisfied: cffi>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from argon2-cffi-bindings->argon2-cffi>=21.1->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (1.17.1)
Requirement already satisfied: pycparser in /usr/local/lib/python3.11/dist-packages (from cffi>=1.0.1->argon2-cffi-bindings->argon2-cffi>=21.1->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py) (2.22)
Requirement already satisfied: notebook-shim>=0.2.3 in /usr/local/lib/python3.11/dist-packages (from nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets->leafmap->geoai-py) (0.2.4)
Collecting arrow>=0.15.0 (from isoduration->jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py)
Downloading arrow-1.3.0-py3-none-any.whl.metadata (7.5 kB)
Collecting types-python-dateutil>=2.8.10 (from arrow>=0.15.0->isoduration->jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server>=1.24.0->jupyter-server-proxy->geoai-py)
Downloading types_python_dateutil-2.9.0.20250708-py3-none-any.whl.metadata (1.9 kB)
Downloading geoai_py-0.8.1-py2.py3-none-any.whl (163 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 163.3/163.3 kB 7.5 MB/s eta 0:00:00
Downloading buildingregulariser-0.2.2-py3-none-any.whl (19 kB)
Downloading contextily-1.6.2-py3-none-any.whl (17 kB)
Downloading jupyter_server_proxy-4.4.0-py3-none-any.whl (37 kB)
Downloading leafmap-0.48.6-py2.py3-none-any.whl (568 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 568.1/568.1 kB 21.9 MB/s eta 0:00:00
Downloading localtileserver-0.10.6-py3-none-any.whl (17.1 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 17.1/17.1 MB 89.8 MB/s eta 0:00:00
Downloading mapclassify-2.9.0-py3-none-any.whl (286 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 286.7/286.7 kB 24.3 MB/s eta 0:00:00
Downloading maplibre-0.3.4-py3-none-any.whl (1.4 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.4/1.4 MB 68.7 MB/s eta 0:00:00
Downloading overturemaps-0.15.0-py3-none-any.whl (9.9 kB)
Downloading planetary_computer-1.0.0-py3-none-any.whl (14 kB)
Downloading pystac_client-0.8.6-py3-none-any.whl (41 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 41.4/41.4 kB 3.3 MB/s eta 0:00:00
Downloading rasterio-1.4.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (22.2 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 22.2/22.2 MB 100.2 MB/s eta 0:00:00
Downloading rioxarray-0.19.0-py3-none-any.whl (62 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 62.2/62.2 kB 5.5 MB/s eta 0:00:00
Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl (363.4 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 363.4/363.4 MB 3.2 MB/s eta 0:00:00
Downloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (13.8 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 13.8/13.8 MB 124.9 MB/s eta 0:00:00
Downloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (24.6 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 24.6/24.6 MB 93.8 MB/s eta 0:00:00
Downloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (883 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 883.7/883.7 kB 58.2 MB/s eta 0:00:00
Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl (664.8 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 664.8/664.8 MB 2.4 MB/s eta 0:00:00
Downloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl (211.5 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 211.5/211.5 MB 5.4 MB/s eta 0:00:00
Downloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl (56.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 56.3/56.3 MB 44.1 MB/s eta 0:00:00
Downloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl (127.9 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 127.9/127.9 MB 19.5 MB/s eta 0:00:00
Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl (207.5 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 207.5/207.5 MB 4.0 MB/s eta 0:00:00
Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 21.1/21.1 MB 108.0 MB/s eta 0:00:00
Downloading torchgeo-0.7.1-py3-none-any.whl (605 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 605.3/605.3 kB 44.7 MB/s eta 0:00:00
Downloading torchinfo-1.8.0-py3-none-any.whl (23 kB)
Downloading cligj-0.7.2-py3-none-any.whl (7.1 kB)
Downloading fiona-1.10.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 17.3/17.3 MB 116.9 MB/s eta 0:00:00
Downloading click_plugins-1.1.1.2-py2.py3-none-any.whl (11 kB)
Downloading flask_restx-1.3.0-py2.py3-none-any.whl (2.8 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.8/2.8 MB 93.4 MB/s eta 0:00:00
Downloading jupyter_server-2.16.0-py3-none-any.whl (386 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 386.9/386.9 kB 33.4 MB/s eta 0:00:00
Downloading kornia-0.8.1-py2.py3-none-any.whl (1.1 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.1/1.1 MB 65.3 MB/s eta 0:00:00
Downloading lightly-1.5.21-py3-none-any.whl (855 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 855.8/855.8 kB 48.6 MB/s eta 0:00:00
Downloading lightning-2.5.2-py3-none-any.whl (821 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 821.1/821.1 kB 56.2 MB/s eta 0:00:00
Downloading pystac-1.13.0-py3-none-any.whl (206 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 206.8/206.8 kB 19.7 MB/s eta 0:00:00
Downloading rtree-1.4.0-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (541 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 541.1/541.1 kB 43.1 MB/s eta 0:00:00
Downloading segmentation_models_pytorch-0.5.0-py3-none-any.whl (154 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 154.8/154.8 kB 16.6 MB/s eta 0:00:00
Downloading simpervisor-1.0.0-py3-none-any.whl (8.3 kB)
Downloading torchmetrics-1.7.4-py3-none-any.whl (963 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 963.5/963.5 kB 61.6 MB/s eta 0:00:00
Downloading affine-2.4.0-py3-none-any.whl (15 kB)
Downloading anywidget-0.9.18-py3-none-any.whl (220 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 220.7/220.7 kB 22.9 MB/s eta 0:00:00
Downloading eval_type_backport-0.2.2-py3-none-any.whl (5.8 kB)
Downloading Flask_Caching-2.3.1-py3-none-any.whl (28 kB)
Downloading flask_cors-6.0.1-py3-none-any.whl (13 kB)
Downloading geojson-3.2.0-py3-none-any.whl (15 kB)
Downloading ipyvuetify-1.11.3-py2.py3-none-any.whl (6.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 6.3/6.3 MB 118.8 MB/s eta 0:00:00
Downloading mercantile-1.2.1-py3-none-any.whl (14 kB)
Downloading python_dotenv-1.1.1-py3-none-any.whl (20 kB)
Downloading rio_cogeo-5.4.2-py3-none-any.whl (21 kB)
Downloading rio_tiler-7.8.1-py3-none-any.whl (269 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 269.1/269.1 kB 27.0 MB/s eta 0:00:00
Downloading server_thread-0.3.0-py3-none-any.whl (6.6 kB)
Downloading whiteboxgui-2.3.0-py2.py3-none-any.whl (108 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 108.6/108.6 kB 12.5 MB/s eta 0:00:00
Downloading aenum-3.1.16-py3-none-any.whl (165 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 165.6/165.6 kB 19.6 MB/s eta 0:00:00
Downloading aniso8601-10.0.1-py2.py3-none-any.whl (52 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 52.8/52.8 kB 5.6 MB/s eta 0:00:00
Downloading bitsandbytes-0.46.1-py3-none-manylinux_2_24_x86_64.whl (72.9 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 72.9/72.9 MB 35.9 MB/s eta 0:00:00
Downloading cachelib-0.13.0-py3-none-any.whl (20 kB)
Downloading hydra_core-1.3.2-py3-none-any.whl (154 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 154.5/154.5 kB 15.9 MB/s eta 0:00:00
Downloading ipyvue-1.11.2-py2.py3-none-any.whl (2.7 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.7/2.7 MB 104.6 MB/s eta 0:00:00
Downloading jsonargparse-4.40.0-py3-none-any.whl (224 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 224.3/224.3 kB 22.4 MB/s eta 0:00:00
Downloading jupyter_events-0.12.0-py3-none-any.whl (19 kB)
Downloading jupyter_server_terminals-0.5.3-py3-none-any.whl (13 kB)
Downloading kornia_rs-0.1.9-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.8 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.8/2.8 MB 78.1 MB/s eta 0:00:00
Downloading lightly_utils-0.0.2-py3-none-any.whl (6.4 kB)
Downloading lightning_utilities-0.14.3-py3-none-any.whl (28 kB)
Downloading morecantile-6.2.0-py3-none-any.whl (49 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 49.5/49.5 kB 5.2 MB/s eta 0:00:00
Downloading overrides-7.7.0-py3-none-any.whl (17 kB)
Downloading psygnal-0.14.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (837 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 837.4/837.4 kB 61.6 MB/s eta 0:00:00
Downloading pytorch_lightning-2.5.2-py3-none-any.whl (825 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 825.4/825.4 kB 62.3 MB/s eta 0:00:00
Downloading tensorboardx-2.6.4-py3-none-any.whl (87 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 87.2/87.2 kB 9.1 MB/s eta 0:00:00
Downloading color_operations-0.2.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (195 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 195.2/195.2 kB 19.4 MB/s eta 0:00:00
Downloading whitebox-2.3.6-py2.py3-none-any.whl (74 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 74.0/74.0 kB 8.0 MB/s eta 0:00:00
Downloading jedi-0.19.2-py2.py3-none-any.whl (1.6 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.6/1.6 MB 80.3 MB/s eta 0:00:00
Downloading jsonnet-0.21.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (6.5 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 6.5/6.5 MB 102.0 MB/s eta 0:00:00
Downloading jupyter_client-7.4.9-py3-none-any.whl (133 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 133.5/133.5 kB 13.1 MB/s eta 0:00:00
Downloading python_json_logger-3.3.0-py3-none-any.whl (15 kB)
Downloading rfc3986_validator-0.1.1-py2.py3-none-any.whl (4.2 kB)
Downloading typeshed_client-2.7.0-py3-none-any.whl (624 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 624.4/624.4 kB 47.2 MB/s eta 0:00:00
Downloading rfc3339_validator-0.1.4-py2.py3-none-any.whl (3.5 kB)
Downloading fqdn-1.5.1-py3-none-any.whl (9.1 kB)
Downloading isoduration-20.11.0-py3-none-any.whl (11 kB)
Downloading uri_template-1.3.0-py3-none-any.whl (11 kB)
Downloading arrow-1.3.0-py3-none-any.whl (66 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 66.4/66.4 kB 7.2 MB/s eta 0:00:00
Downloading types_python_dateutil-2.9.0.20250708-py3-none-any.whl (17 kB)
Installing collected packages: jsonnet, aniso8601, aenum, whitebox, uri-template, typeshed-client, types-python-dateutil, torchinfo, tensorboardX, simpervisor, rtree, rfc3986-validator, rfc3339-validator, python-json-logger, python-dotenv, psygnal, overrides, nvidia-nvjitlink-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, mercantile, lightning-utilities, lightly_utils, kornia_rs, jsonargparse, jedi, geojson, fqdn, eval-type-backport, color-operations, cligj, click-plugins, cachelib, affine, server-thread, rasterio, pystac, overturemaps, nvidia-cusparse-cu12, nvidia-cudnn-cu12, jupyter-server-terminals, jupyter-client, hydra-core, fiona, arrow, nvidia-cusolver-cu12, morecantile, maplibre, mapclassify, isoduration, flask-cors, Flask-Caching, contextily, rioxarray, rio-tiler, rio-cogeo, flask-restx, buildingregulariser, torchmetrics, pystac-client, localtileserver, kornia, jupyter-events, bitsandbytes, pytorch_lightning, planetary-computer, segmentation-models-pytorch, lightning, lightly, jupyter-server, jupyter-server-proxy, torchgeo, ipyvue, anywidget, whiteboxgui, ipyvuetify, leafmap, geoai-py
Attempting uninstall: nvidia-nvjitlink-cu12
Found existing installation: nvidia-nvjitlink-cu12 12.5.82
Uninstalling nvidia-nvjitlink-cu12-12.5.82:
Successfully uninstalled nvidia-nvjitlink-cu12-12.5.82
Attempting uninstall: nvidia-curand-cu12
Found existing installation: nvidia-curand-cu12 10.3.6.82
Uninstalling nvidia-curand-cu12-10.3.6.82:
Successfully uninstalled nvidia-curand-cu12-10.3.6.82
Attempting uninstall: nvidia-cufft-cu12
Found existing installation: nvidia-cufft-cu12 11.2.3.61
Uninstalling nvidia-cufft-cu12-11.2.3.61:
Successfully uninstalled nvidia-cufft-cu12-11.2.3.61
Attempting uninstall: nvidia-cuda-runtime-cu12
Found existing installation: nvidia-cuda-runtime-cu12 12.5.82
Uninstalling nvidia-cuda-runtime-cu12-12.5.82:
Successfully uninstalled nvidia-cuda-runtime-cu12-12.5.82
Attempting uninstall: nvidia-cuda-nvrtc-cu12
Found existing installation: nvidia-cuda-nvrtc-cu12 12.5.82
Uninstalling nvidia-cuda-nvrtc-cu12-12.5.82:
Successfully uninstalled nvidia-cuda-nvrtc-cu12-12.5.82
Attempting uninstall: nvidia-cuda-cupti-cu12
Found existing installation: nvidia-cuda-cupti-cu12 12.5.82
Uninstalling nvidia-cuda-cupti-cu12-12.5.82:
Successfully uninstalled nvidia-cuda-cupti-cu12-12.5.82
Attempting uninstall: nvidia-cublas-cu12
Found existing installation: nvidia-cublas-cu12 12.5.3.2
Uninstalling nvidia-cublas-cu12-12.5.3.2:
Successfully uninstalled nvidia-cublas-cu12-12.5.3.2
Attempting uninstall: nvidia-cusparse-cu12
Found existing installation: nvidia-cusparse-cu12 12.5.1.3
Uninstalling nvidia-cusparse-cu12-12.5.1.3:
Successfully uninstalled nvidia-cusparse-cu12-12.5.1.3
Attempting uninstall: nvidia-cudnn-cu12
Found existing installation: nvidia-cudnn-cu12 9.3.0.75
Uninstalling nvidia-cudnn-cu12-9.3.0.75:
Successfully uninstalled nvidia-cudnn-cu12-9.3.0.75
Attempting uninstall: jupyter-client
Found existing installation: jupyter-client 6.1.12
Uninstalling jupyter-client-6.1.12:
Successfully uninstalled jupyter-client-6.1.12
Attempting uninstall: nvidia-cusolver-cu12
Found existing installation: nvidia-cusolver-cu12 11.6.3.83
Uninstalling nvidia-cusolver-cu12-11.6.3.83:
Successfully uninstalled nvidia-cusolver-cu12-11.6.3.83
Attempting uninstall: jupyter-server
Found existing installation: jupyter-server 1.16.0
Uninstalling jupyter-server-1.16.0:
Successfully uninstalled jupyter-server-1.16.0
Successfully installed Flask-Caching-2.3.1 aenum-3.1.16 affine-2.4.0 aniso8601-10.0.1 anywidget-0.9.18 arrow-1.3.0 bitsandbytes-0.46.1 buildingregulariser-0.2.2 cachelib-0.13.0 click-plugins-1.1.1.2 cligj-0.7.2 color-operations-0.2.0 contextily-1.6.2 eval-type-backport-0.2.2 fiona-1.10.1 flask-cors-6.0.1 flask-restx-1.3.0 fqdn-1.5.1 geoai-py-0.8.1 geojson-3.2.0 hydra-core-1.3.2 ipyvue-1.11.2 ipyvuetify-1.11.3 isoduration-20.11.0 jedi-0.19.2 jsonargparse-4.40.0 jsonnet-0.21.0 jupyter-client-7.4.9 jupyter-events-0.12.0 jupyter-server-2.16.0 jupyter-server-proxy-4.4.0 jupyter-server-terminals-0.5.3 kornia-0.8.1 kornia_rs-0.1.9 leafmap-0.48.6 lightly-1.5.21 lightly_utils-0.0.2 lightning-2.5.2 lightning-utilities-0.14.3 localtileserver-0.10.6 mapclassify-2.9.0 maplibre-0.3.4 mercantile-1.2.1 morecantile-6.2.0 nvidia-cublas-cu12-12.4.5.8 nvidia-cuda-cupti-cu12-12.4.127 nvidia-cuda-nvrtc-cu12-12.4.127 nvidia-cuda-runtime-cu12-12.4.127 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.2.1.3 nvidia-curand-cu12-10.3.5.147 nvidia-cusolver-cu12-11.6.1.9 nvidia-cusparse-cu12-12.3.1.170 nvidia-nvjitlink-cu12-12.4.127 overrides-7.7.0 overturemaps-0.15.0 planetary-computer-1.0.0 psygnal-0.14.0 pystac-1.13.0 pystac-client-0.8.6 python-dotenv-1.1.1 python-json-logger-3.3.0 pytorch_lightning-2.5.2 rasterio-1.4.3 rfc3339-validator-0.1.4 rfc3986-validator-0.1.1 rio-cogeo-5.4.2 rio-tiler-7.8.1 rioxarray-0.19.0 rtree-1.4.0 segmentation-models-pytorch-0.5.0 server-thread-0.3.0 simpervisor-1.0.0 tensorboardX-2.6.4 torchgeo-0.7.1 torchinfo-1.8.0 torchmetrics-1.7.4 types-python-dateutil-2.9.0.20250708 typeshed-client-2.7.0 uri-template-1.3.0 whitebox-2.3.6 whiteboxgui-2.3.0
Collecting ipysheet
Downloading ipysheet-0.7.0-py2.py3-none-any.whl.metadata (4.0 kB)
Requirement already satisfied: ipywidgets<9.0,>=7.5.0 in /usr/local/lib/python3.11/dist-packages (from ipysheet) (7.7.1)
Requirement already satisfied: ipykernel>=4.5.1 in /usr/local/lib/python3.11/dist-packages (from ipywidgets<9.0,>=7.5.0->ipysheet) (6.17.1)
Requirement already satisfied: ipython-genutils~=0.2.0 in /usr/local/lib/python3.11/dist-packages (from ipywidgets<9.0,>=7.5.0->ipysheet) (0.2.0)
Requirement already satisfied: traitlets>=4.3.1 in /usr/local/lib/python3.11/dist-packages (from ipywidgets<9.0,>=7.5.0->ipysheet) (5.7.1)
Requirement already satisfied: widgetsnbextension~=3.6.0 in /usr/local/lib/python3.11/dist-packages (from ipywidgets<9.0,>=7.5.0->ipysheet) (3.6.10)
Requirement already satisfied: ipython>=4.0.0 in /usr/local/lib/python3.11/dist-packages (from ipywidgets<9.0,>=7.5.0->ipysheet) (7.34.0)
Requirement already satisfied: jupyterlab-widgets>=1.0.0 in /usr/local/lib/python3.11/dist-packages (from ipywidgets<9.0,>=7.5.0->ipysheet) (3.0.15)
Requirement already satisfied: debugpy>=1.0 in /usr/local/lib/python3.11/dist-packages (from ipykernel>=4.5.1->ipywidgets<9.0,>=7.5.0->ipysheet) (1.8.0)
Requirement already satisfied: jupyter-client>=6.1.12 in /usr/local/lib/python3.11/dist-packages (from ipykernel>=4.5.1->ipywidgets<9.0,>=7.5.0->ipysheet) (7.4.9)
Requirement already satisfied: matplotlib-inline>=0.1 in /usr/local/lib/python3.11/dist-packages (from ipykernel>=4.5.1->ipywidgets<9.0,>=7.5.0->ipysheet) (0.1.7)
Requirement already satisfied: nest-asyncio in /usr/local/lib/python3.11/dist-packages (from ipykernel>=4.5.1->ipywidgets<9.0,>=7.5.0->ipysheet) (1.6.0)
Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from ipykernel>=4.5.1->ipywidgets<9.0,>=7.5.0->ipysheet) (24.2)
Requirement already satisfied: psutil in /usr/local/lib/python3.11/dist-packages (from ipykernel>=4.5.1->ipywidgets<9.0,>=7.5.0->ipysheet) (5.9.5)
Requirement already satisfied: pyzmq>=17 in /usr/local/lib/python3.11/dist-packages (from ipykernel>=4.5.1->ipywidgets<9.0,>=7.5.0->ipysheet) (24.0.1)
Requirement already satisfied: tornado>=6.1 in /usr/local/lib/python3.11/dist-packages (from ipykernel>=4.5.1->ipywidgets<9.0,>=7.5.0->ipysheet) (6.4.2)
Requirement already satisfied: setuptools>=18.5 in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets<9.0,>=7.5.0->ipysheet) (75.2.0)
Requirement already satisfied: jedi>=0.16 in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.19.2)
Requirement already satisfied: decorator in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets<9.0,>=7.5.0->ipysheet) (4.4.2)
Requirement already satisfied: pickleshare in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.7.5)
Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets<9.0,>=7.5.0->ipysheet) (3.0.51)
Requirement already satisfied: pygments in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets<9.0,>=7.5.0->ipysheet) (2.19.2)
Requirement already satisfied: backcall in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.2.0)
Requirement already satisfied: pexpect>4.3 in /usr/local/lib/python3.11/dist-packages (from ipython>=4.0.0->ipywidgets<9.0,>=7.5.0->ipysheet) (4.9.0)
Requirement already satisfied: notebook>=4.4.1 in /usr/local/lib/python3.11/dist-packages (from widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (6.5.7)
Requirement already satisfied: parso<0.9.0,>=0.8.4 in /usr/local/lib/python3.11/dist-packages (from jedi>=0.16->ipython>=4.0.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.8.4)
Requirement already satisfied: entrypoints in /usr/local/lib/python3.11/dist-packages (from jupyter-client>=6.1.12->ipykernel>=4.5.1->ipywidgets<9.0,>=7.5.0->ipysheet) (0.4)
Requirement already satisfied: jupyter-core>=4.9.2 in /usr/local/lib/python3.11/dist-packages (from jupyter-client>=6.1.12->ipykernel>=4.5.1->ipywidgets<9.0,>=7.5.0->ipysheet) (5.8.1)
Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from jupyter-client>=6.1.12->ipykernel>=4.5.1->ipywidgets<9.0,>=7.5.0->ipysheet) (2.9.0.post0)
Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (3.1.6)
Requirement already satisfied: argon2-cffi in /usr/local/lib/python3.11/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (25.1.0)
Requirement already satisfied: nbformat in /usr/local/lib/python3.11/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (5.10.4)
Requirement already satisfied: nbconvert>=5 in /usr/local/lib/python3.11/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (7.16.6)
Requirement already satisfied: Send2Trash>=1.8.0 in /usr/local/lib/python3.11/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (1.8.3)
Requirement already satisfied: terminado>=0.8.3 in /usr/local/lib/python3.11/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.18.1)
Requirement already satisfied: prometheus-client in /usr/local/lib/python3.11/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.22.1)
Requirement already satisfied: nbclassic>=0.4.7 in /usr/local/lib/python3.11/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (1.3.1)
Requirement already satisfied: ptyprocess>=0.5 in /usr/local/lib/python3.11/dist-packages (from pexpect>4.3->ipython>=4.0.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.7.0)
Requirement already satisfied: wcwidth in /usr/local/lib/python3.11/dist-packages (from prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0->ipython>=4.0.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.2.13)
Requirement already satisfied: platformdirs>=2.5 in /usr/local/lib/python3.11/dist-packages (from jupyter-core>=4.9.2->jupyter-client>=6.1.12->ipykernel>=4.5.1->ipywidgets<9.0,>=7.5.0->ipysheet) (4.3.8)
Requirement already satisfied: notebook-shim>=0.2.3 in /usr/local/lib/python3.11/dist-packages (from nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.2.4)
Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.11/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (4.13.4)
Requirement already satisfied: bleach!=5.0.0 in /usr/local/lib/python3.11/dist-packages (from bleach[css]!=5.0.0->nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (6.2.0)
Requirement already satisfied: defusedxml in /usr/local/lib/python3.11/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.7.1)
Requirement already satisfied: jupyterlab-pygments in /usr/local/lib/python3.11/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.3.0)
Requirement already satisfied: markupsafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (3.0.2)
Requirement already satisfied: mistune<4,>=2.0.3 in /usr/local/lib/python3.11/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (3.1.3)
Requirement already satisfied: nbclient>=0.5.0 in /usr/local/lib/python3.11/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.10.2)
Requirement already satisfied: pandocfilters>=1.4.1 in /usr/local/lib/python3.11/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (1.5.1)
Requirement already satisfied: fastjsonschema>=2.15 in /usr/local/lib/python3.11/dist-packages (from nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (2.21.1)
Requirement already satisfied: jsonschema>=2.6 in /usr/local/lib/python3.11/dist-packages (from nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (4.24.0)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->jupyter-client>=6.1.12->ipykernel>=4.5.1->ipywidgets<9.0,>=7.5.0->ipysheet) (1.17.0)
Requirement already satisfied: argon2-cffi-bindings in /usr/local/lib/python3.11/dist-packages (from argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (21.2.0)
Requirement already satisfied: webencodings in /usr/local/lib/python3.11/dist-packages (from bleach!=5.0.0->bleach[css]!=5.0.0->nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.5.1)
Requirement already satisfied: tinycss2<1.5,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from bleach[css]!=5.0.0->nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (1.4.0)
Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.11/dist-packages (from jsonschema>=2.6->nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (25.3.0)
Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.11/dist-packages (from jsonschema>=2.6->nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (2025.4.1)
Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.11/dist-packages (from jsonschema>=2.6->nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.36.2)
Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.11/dist-packages (from jsonschema>=2.6->nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.26.0)
Requirement already satisfied: jupyter-server<3,>=1.8 in /usr/local/lib/python3.11/dist-packages (from notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (2.16.0)
Requirement already satisfied: cffi>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from argon2-cffi-bindings->argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (1.17.1)
Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.11/dist-packages (from beautifulsoup4->nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (2.7)
Requirement already satisfied: typing-extensions>=4.0.0 in /usr/local/lib/python3.11/dist-packages (from beautifulsoup4->nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (4.14.0)
Requirement already satisfied: pycparser in /usr/local/lib/python3.11/dist-packages (from cffi>=1.0.1->argon2-cffi-bindings->argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (2.22)
Requirement already satisfied: anyio>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (4.9.0)
Requirement already satisfied: jupyter-events>=0.11.0 in /usr/local/lib/python3.11/dist-packages (from jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.12.0)
Requirement already satisfied: jupyter-server-terminals>=0.4.4 in /usr/local/lib/python3.11/dist-packages (from jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.5.3)
Requirement already satisfied: overrides>=5.0 in /usr/local/lib/python3.11/dist-packages (from jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (7.7.0)
Requirement already satisfied: websocket-client>=1.7 in /usr/local/lib/python3.11/dist-packages (from jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (1.8.0)
Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.11/dist-packages (from anyio>=3.1.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (3.10)
Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.11/dist-packages (from anyio>=3.1.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (1.3.1)
Requirement already satisfied: python-json-logger>=2.0.4 in /usr/local/lib/python3.11/dist-packages (from jupyter-events>=0.11.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (3.3.0)
Requirement already satisfied: pyyaml>=5.3 in /usr/local/lib/python3.11/dist-packages (from jupyter-events>=0.11.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (6.0.2)
Requirement already satisfied: rfc3339-validator in /usr/local/lib/python3.11/dist-packages (from jupyter-events>=0.11.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.1.4)
Requirement already satisfied: rfc3986-validator>=0.1.1 in /usr/local/lib/python3.11/dist-packages (from jupyter-events>=0.11.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (0.1.1)
Requirement already satisfied: fqdn in /usr/local/lib/python3.11/dist-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (1.5.1)
Requirement already satisfied: isoduration in /usr/local/lib/python3.11/dist-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (20.11.0)
Requirement already satisfied: jsonpointer>1.13 in /usr/local/lib/python3.11/dist-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (3.0.0)
Requirement already satisfied: uri-template in /usr/local/lib/python3.11/dist-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (1.3.0)
Requirement already satisfied: webcolors>=24.6.0 in /usr/local/lib/python3.11/dist-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (24.11.1)
Requirement already satisfied: arrow>=0.15.0 in /usr/local/lib/python3.11/dist-packages (from isoduration->jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (1.3.0)
Requirement already satisfied: types-python-dateutil>=2.8.10 in /usr/local/lib/python3.11/dist-packages (from arrow>=0.15.0->isoduration->jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.11.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets<9.0,>=7.5.0->ipysheet) (2.9.0.20250708)
Downloading ipysheet-0.7.0-py2.py3-none-any.whl (3.8 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.8/3.8 MB 33.0 MB/s eta 0:00:00
Installing collected packages: ipysheet
Successfully installed ipysheet-0.7.0
Requirement already satisfied: rasterio in /usr/local/lib/python3.11/dist-packages (1.4.3)
Requirement already satisfied: affine in /usr/local/lib/python3.11/dist-packages (from rasterio) (2.4.0)
Requirement already satisfied: attrs in /usr/local/lib/python3.11/dist-packages (from rasterio) (25.3.0)
Requirement already satisfied: certifi in /usr/local/lib/python3.11/dist-packages (from rasterio) (2025.6.15)
Requirement already satisfied: click>=4.0 in /usr/local/lib/python3.11/dist-packages (from rasterio) (8.2.1)
Requirement already satisfied: cligj>=0.5 in /usr/local/lib/python3.11/dist-packages (from rasterio) (0.7.2)
Requirement already satisfied: numpy>=1.24 in /usr/local/lib/python3.11/dist-packages (from rasterio) (2.0.2)
Requirement already satisfied: click-plugins in /usr/local/lib/python3.11/dist-packages (from rasterio) (1.1.1.2)
Requirement already satisfied: pyparsing in /usr/local/lib/python3.11/dist-packages (from rasterio) (3.2.3)
We connect to Drive and configure the image paths:
In [ ]:
from google.colab import drive
drive.mount('/content/drive')
Mounted at /content/drive
In [ ]:
import geoai
import leafmap
import rasterio
In [ ]:
train_image = '/content/drive/MyDrive/Datasets/Landcover_AI/images/M-33-20-D-c-4-2.tif'
test_image = '/content/drive/MyDrive/Datasets/Landcover_AI/images/M-33-20-D-d-3-3.tif'
train_mask = '/content/drive/MyDrive/Datasets/Landcover_AI/masks/M-33-20-D-c-4-2.tif'
In [ ]:
images_dir = '/content/drive/MyDrive/Datasets/Naip_chesapeak/naip_images'
masks_dir = '/content/drive/MyDrive/Datasets/Naip_chesapeak/chesapeake_labels'
In [ ]:
train_image = '/content/drive/MyDrive/Datasets/Naip_chesapeak/naip_images/m_3807512_sw_18_060_20180815.tif'
train_mask = '/content/drive/MyDrive/Datasets/Naip_chesapeak/chesapeake_labels/m_3807512_sw_18_060_20180815.tif'
m = leafmap.Map()
m.add_raster(train_image, layer_name="Satellite Image")
m.add_raster(train_mask, cmap='inferno', layer_name="Mask")
m
Let's divide the images and masks into 512x512 patches:
In [ ]:
out_folder = "/content/tiles"
tiles = geoai.export_geotiff_tiles_batch(
images_folder=images_dir,
masks_folder=masks_dir,
output_folder=out_folder,
tile_size=512,
stride=256,
quiet=True,
)
We can view the generated tiles:
In [ ]:
import os
import matplotlib.pyplot as plt
import rasterio
image_folder = '/content/tiles/images'
label_folder = '/content/tiles/masks'
# Get a list of all image and label files
image_files = [f for f in os.listdir(image_folder) if f.endswith('.tif')]
label_files = [f for f in os.listdir(label_folder) if f.endswith('.tif')]
# Assuming image and label files have the same base name
image_files.sort()
label_files.sort()
# Visualize the first few pairs of image and mask
num_to_visualize = min(len(image_files), 5) # Visualize up to 5 pairs
for i in range(num_to_visualize):
image_path = os.path.join(image_folder, image_files[i])
label_path = os.path.join(label_folder, label_files[i])
with rasterio.open(image_path) as src_img:
image = src_img.read()
with rasterio.open(label_path) as src_mask:
mask = src_mask.read(1) # Read only the first band for the mask
# Plotting
fig, axes = plt.subplots(1, 2, figsize=(10, 5))
# Plot image (assuming it's a multi-band image, e.g., RGB)
# Transpose the image data to be in (height, width, channels) format for matplotlib
image_transposed = image.transpose(1, 2, 0)
axes[0].imshow(image_transposed)
axes[0].set_title(f'Image: {image_files[i]}')
axes[0].axis('off')
# Plot mask
axes[1].imshow(mask, cmap='inferno') # Use a colormap for the mask
axes[1].set_title(f'Mask: {label_files[i]}')
axes[1].axis('off')
plt.tight_layout()
plt.show()
Then we train U-Net for 20 epochs:
In [ ]:
geoai.train_segmentation_model(
images_dir=f"{out_folder}/images",
labels_dir=f"{out_folder}/masks",
output_dir=f"{out_folder}/unet_models",
architecture="unet",
encoder_name="resnet34",
encoder_weights="imagenet",
num_channels=4,
num_classes=13,
batch_size=8,
num_epochs=20,
learning_rate=0.001,
val_split=0.2,
verbose=True,
plot_curves=True,
)
Using device: cuda Found 7566 image files and 7566 label files Training on 6052 images, validating on 1514 images Checking image sizes for compatibility... All sampled images have the same size: (512, 512) No resizing needed. Testing data loader... Data loader test passed.
config.json: 0%| | 0.00/156 [00:00<?, ?B/s]
model.safetensors: 0%| | 0.00/87.3M [00:00<?, ?B/s]
Starting training with unet + resnet34 Model parameters: 24,441,245 Epoch: 0, Batch: 0/757, Loss: 2.7731, Time: 1.89s Epoch: 0, Batch: 10/757, Loss: 1.5072, Time: 4.40s Epoch: 0, Batch: 20/757, Loss: 1.5241, Time: 4.40s Epoch: 0, Batch: 30/757, Loss: 0.7965, Time: 4.42s Epoch: 0, Batch: 40/757, Loss: 1.0683, Time: 4.45s Epoch: 0, Batch: 50/757, Loss: 0.9814, Time: 4.46s Epoch: 0, Batch: 60/757, Loss: 1.0523, Time: 4.46s Epoch: 0, Batch: 70/757, Loss: 0.5196, Time: 4.46s Epoch: 0, Batch: 80/757, Loss: 0.8431, Time: 4.48s Epoch: 0, Batch: 90/757, Loss: 1.3484, Time: 4.49s Epoch: 0, Batch: 100/757, Loss: 0.6793, Time: 4.50s Epoch: 0, Batch: 110/757, Loss: 0.7023, Time: 4.52s Epoch: 0, Batch: 120/757, Loss: 1.0879, Time: 4.53s Epoch: 0, Batch: 130/757, Loss: 1.1761, Time: 4.55s Epoch: 0, Batch: 140/757, Loss: 0.7488, Time: 4.55s Epoch: 0, Batch: 150/757, Loss: 0.5740, Time: 4.56s Epoch: 0, Batch: 160/757, Loss: 0.4987, Time: 4.58s Epoch: 0, Batch: 170/757, Loss: 0.6278, Time: 4.59s Epoch: 0, Batch: 180/757, Loss: 0.5622, Time: 4.60s Epoch: 0, Batch: 190/757, Loss: 0.8205, Time: 4.61s Epoch: 0, Batch: 200/757, Loss: 0.5861, Time: 4.63s Epoch: 0, Batch: 210/757, Loss: 1.1496, Time: 4.64s Epoch: 0, Batch: 220/757, Loss: 1.2396, Time: 4.66s Epoch: 0, Batch: 230/757, Loss: 1.0449, Time: 4.66s Epoch: 0, Batch: 240/757, Loss: 0.8463, Time: 4.66s Epoch: 0, Batch: 250/757, Loss: 0.5436, Time: 4.66s Epoch: 0, Batch: 260/757, Loss: 0.6174, Time: 4.66s Epoch: 0, Batch: 270/757, Loss: 1.0457, Time: 4.66s Epoch: 0, Batch: 280/757, Loss: 0.6107, Time: 4.68s Epoch: 0, Batch: 290/757, Loss: 0.6048, Time: 4.69s Epoch: 0, Batch: 300/757, Loss: 0.7741, Time: 4.70s Epoch: 0, Batch: 310/757, Loss: 0.5988, Time: 4.70s Epoch: 0, Batch: 320/757, Loss: 0.4053, Time: 4.71s Epoch: 0, Batch: 330/757, Loss: 0.7419, Time: 4.71s Epoch: 0, Batch: 340/757, Loss: 1.0679, Time: 4.73s Epoch: 0, Batch: 350/757, Loss: 0.8181, Time: 4.74s Epoch: 0, Batch: 360/757, Loss: 0.6684, Time: 4.74s Epoch: 0, Batch: 370/757, Loss: 0.6689, Time: 4.75s Epoch: 0, Batch: 380/757, Loss: 0.6563, Time: 4.75s Epoch: 0, Batch: 390/757, Loss: 0.4748, Time: 4.75s Epoch: 0, Batch: 400/757, Loss: 0.9352, Time: 4.76s Epoch: 0, Batch: 410/757, Loss: 0.5988, Time: 4.76s Epoch: 0, Batch: 420/757, Loss: 0.9726, Time: 4.77s Epoch: 0, Batch: 430/757, Loss: 0.6344, Time: 4.77s Epoch: 0, Batch: 440/757, Loss: 0.7998, Time: 4.78s Epoch: 0, Batch: 450/757, Loss: 0.6945, Time: 4.79s Epoch: 0, Batch: 460/757, Loss: 0.4817, Time: 4.78s Epoch: 0, Batch: 470/757, Loss: 0.3249, Time: 4.79s Epoch: 0, Batch: 480/757, Loss: 0.6167, Time: 4.79s Epoch: 0, Batch: 490/757, Loss: 0.6574, Time: 4.79s Epoch: 0, Batch: 500/757, Loss: 0.4112, Time: 4.80s Epoch: 0, Batch: 510/757, Loss: 0.8207, Time: 4.80s Epoch: 0, Batch: 520/757, Loss: 0.6267, Time: 4.81s Epoch: 0, Batch: 530/757, Loss: 0.4672, Time: 4.81s Epoch: 0, Batch: 540/757, Loss: 0.7546, Time: 4.81s Epoch: 0, Batch: 550/757, Loss: 0.3490, Time: 4.81s Epoch: 0, Batch: 560/757, Loss: 0.4513, Time: 4.81s Epoch: 0, Batch: 570/757, Loss: 0.6643, Time: 4.82s Epoch: 0, Batch: 580/757, Loss: 0.4109, Time: 4.82s Epoch: 0, Batch: 590/757, Loss: 0.5075, Time: 4.82s Epoch: 0, Batch: 600/757, Loss: 0.5223, Time: 4.83s Epoch: 0, Batch: 610/757, Loss: 1.1354, Time: 4.82s Epoch: 0, Batch: 620/757, Loss: 0.3331, Time: 4.83s Epoch: 0, Batch: 630/757, Loss: 0.7121, Time: 4.83s Epoch: 0, Batch: 640/757, Loss: 0.5809, Time: 4.82s Epoch: 0, Batch: 650/757, Loss: 0.5152, Time: 4.82s Epoch: 0, Batch: 660/757, Loss: 0.3458, Time: 4.83s Epoch: 0, Batch: 670/757, Loss: 1.0068, Time: 4.82s Epoch: 0, Batch: 680/757, Loss: 0.6020, Time: 4.82s Epoch: 0, Batch: 690/757, Loss: 0.5084, Time: 4.83s Epoch: 0, Batch: 700/757, Loss: 0.6284, Time: 4.83s Epoch: 0, Batch: 710/757, Loss: 0.6269, Time: 4.84s Epoch: 0, Batch: 720/757, Loss: 0.7124, Time: 4.84s Epoch: 0, Batch: 730/757, Loss: 0.9872, Time: 4.83s Epoch: 0, Batch: 740/757, Loss: 0.7325, Time: 4.84s Epoch: 0, Batch: 750/757, Loss: 0.5714, Time: 4.84s Epoch 1/20: Train Loss: 0.7145, Val Loss: 0.8461, Val IoU: 0.2150, Val Dice: 0.2436 Saving best model with IoU: 0.2150 Epoch: 1, Batch: 0/757, Loss: 0.5255, Time: 0.90s Epoch: 1, Batch: 10/757, Loss: 0.5144, Time: 4.84s Epoch: 1, Batch: 20/757, Loss: 0.6648, Time: 4.85s Epoch: 1, Batch: 30/757, Loss: 1.0540, Time: 4.84s Epoch: 1, Batch: 40/757, Loss: 0.5518, Time: 4.85s Epoch: 1, Batch: 50/757, Loss: 0.3585, Time: 4.86s Epoch: 1, Batch: 60/757, Loss: 0.5302, Time: 4.85s Epoch: 1, Batch: 70/757, Loss: 0.6854, Time: 4.85s Epoch: 1, Batch: 80/757, Loss: 0.7231, Time: 4.85s Epoch: 1, Batch: 90/757, Loss: 0.9712, Time: 4.85s Epoch: 1, Batch: 100/757, Loss: 0.8302, Time: 4.86s Epoch: 1, Batch: 110/757, Loss: 0.3634, Time: 4.86s Epoch: 1, Batch: 120/757, Loss: 0.7904, Time: 4.86s Epoch: 1, Batch: 130/757, Loss: 0.4077, Time: 4.85s Epoch: 1, Batch: 140/757, Loss: 0.4284, Time: 4.86s Epoch: 1, Batch: 150/757, Loss: 0.8341, Time: 4.86s Epoch: 1, Batch: 160/757, Loss: 0.5447, Time: 4.85s Epoch: 1, Batch: 170/757, Loss: 0.9115, Time: 4.85s Epoch: 1, Batch: 180/757, Loss: 0.8555, Time: 4.86s Epoch: 1, Batch: 190/757, Loss: 0.4933, Time: 4.86s Epoch: 1, Batch: 200/757, Loss: 0.9441, Time: 4.85s Epoch: 1, Batch: 210/757, Loss: 0.6689, Time: 4.85s Epoch: 1, Batch: 220/757, Loss: 0.4032, Time: 4.85s Epoch: 1, Batch: 230/757, Loss: 0.8146, Time: 4.85s Epoch: 1, Batch: 240/757, Loss: 0.3203, Time: 4.86s Epoch: 1, Batch: 250/757, Loss: 0.2939, Time: 4.86s Epoch: 1, Batch: 260/757, Loss: 0.7218, Time: 4.86s Epoch: 1, Batch: 270/757, Loss: 0.8464, Time: 4.86s Epoch: 1, Batch: 280/757, Loss: 0.8351, Time: 4.85s Epoch: 1, Batch: 290/757, Loss: 0.7314, Time: 4.85s Epoch: 1, Batch: 300/757, Loss: 0.6299, Time: 4.86s Epoch: 1, Batch: 310/757, Loss: 0.4800, Time: 4.85s Epoch: 1, Batch: 320/757, Loss: 0.6656, Time: 4.85s Epoch: 1, Batch: 330/757, Loss: 0.8150, Time: 4.85s Epoch: 1, Batch: 340/757, Loss: 0.5749, Time: 4.85s Epoch: 1, Batch: 350/757, Loss: 0.4549, Time: 4.85s Epoch: 1, Batch: 360/757, Loss: 0.5590, Time: 4.85s Epoch: 1, Batch: 370/757, Loss: 0.8624, Time: 4.85s Epoch: 1, Batch: 380/757, Loss: 0.7424, Time: 4.85s Epoch: 1, Batch: 390/757, Loss: 0.5731, Time: 4.84s Epoch: 1, Batch: 400/757, Loss: 0.6032, Time: 4.85s Epoch: 1, Batch: 410/757, Loss: 0.5693, Time: 4.85s Epoch: 1, Batch: 420/757, Loss: 0.6135, Time: 4.86s Epoch: 1, Batch: 430/757, Loss: 0.6163, Time: 4.85s Epoch: 1, Batch: 440/757, Loss: 1.1099, Time: 4.85s Epoch: 1, Batch: 450/757, Loss: 0.5964, Time: 4.86s Epoch: 1, Batch: 460/757, Loss: 0.4745, Time: 4.86s Epoch: 1, Batch: 470/757, Loss: 0.8038, Time: 4.86s Epoch: 1, Batch: 480/757, Loss: 0.7877, Time: 4.86s Epoch: 1, Batch: 490/757, Loss: 0.4094, Time: 4.87s Epoch: 1, Batch: 500/757, Loss: 1.2364, Time: 4.86s Epoch: 1, Batch: 510/757, Loss: 0.6374, Time: 4.86s Epoch: 1, Batch: 520/757, Loss: 0.3598, Time: 4.86s Epoch: 1, Batch: 530/757, Loss: 0.5792, Time: 4.86s Epoch: 1, Batch: 540/757, Loss: 0.9219, Time: 4.86s Epoch: 1, Batch: 550/757, Loss: 0.3606, Time: 4.86s Epoch: 1, Batch: 560/757, Loss: 0.9282, Time: 4.86s Epoch: 1, Batch: 570/757, Loss: 0.8278, Time: 4.86s Epoch: 1, Batch: 580/757, Loss: 0.4378, Time: 4.86s Epoch: 1, Batch: 590/757, Loss: 0.7411, Time: 4.86s Epoch: 1, Batch: 600/757, Loss: 0.4789, Time: 4.86s Epoch: 1, Batch: 610/757, Loss: 0.5795, Time: 4.86s Epoch: 1, Batch: 620/757, Loss: 1.0250, Time: 4.87s Epoch: 1, Batch: 630/757, Loss: 0.6576, Time: 4.86s Epoch: 1, Batch: 640/757, Loss: 0.9604, Time: 4.87s Epoch: 1, Batch: 650/757, Loss: 0.7458, Time: 4.86s Epoch: 1, Batch: 660/757, Loss: 0.7594, Time: 4.87s Epoch: 1, Batch: 670/757, Loss: 0.5370, Time: 4.87s Epoch: 1, Batch: 680/757, Loss: 0.7676, Time: 4.87s Epoch: 1, Batch: 690/757, Loss: 0.6657, Time: 4.86s Epoch: 1, Batch: 700/757, Loss: 0.6302, Time: 4.86s Epoch: 1, Batch: 710/757, Loss: 0.2828, Time: 4.87s Epoch: 1, Batch: 720/757, Loss: 0.5078, Time: 4.87s Epoch: 1, Batch: 730/757, Loss: 0.9537, Time: 4.87s Epoch: 1, Batch: 740/757, Loss: 0.5017, Time: 4.87s Epoch: 1, Batch: 750/757, Loss: 1.1232, Time: 4.87s Epoch 2/20: Train Loss: 0.6314, Val Loss: 0.5986, Val IoU: 0.3097, Val Dice: 0.3453 Saving best model with IoU: 0.3097 Epoch: 2, Batch: 0/757, Loss: 0.6110, Time: 0.86s Epoch: 2, Batch: 10/757, Loss: 0.7208, Time: 4.87s Epoch: 2, Batch: 20/757, Loss: 0.3885, Time: 4.87s Epoch: 2, Batch: 30/757, Loss: 0.4620, Time: 4.87s Epoch: 2, Batch: 40/757, Loss: 0.6761, Time: 4.86s Epoch: 2, Batch: 50/757, Loss: 0.6375, Time: 4.86s Epoch: 2, Batch: 60/757, Loss: 0.5973, Time: 4.86s Epoch: 2, Batch: 70/757, Loss: 0.6721, Time: 4.86s Epoch: 2, Batch: 80/757, Loss: 0.6034, Time: 4.86s Epoch: 2, Batch: 90/757, Loss: 0.5035, Time: 4.86s Epoch: 2, Batch: 100/757, Loss: 0.3549, Time: 4.86s Epoch: 2, Batch: 110/757, Loss: 1.1034, Time: 4.87s Epoch: 2, Batch: 120/757, Loss: 0.6165, Time: 4.86s Epoch: 2, Batch: 130/757, Loss: 0.4143, Time: 4.86s Epoch: 2, Batch: 140/757, Loss: 0.5105, Time: 4.87s Epoch: 2, Batch: 150/757, Loss: 0.9837, Time: 4.86s Epoch: 2, Batch: 160/757, Loss: 0.5361, Time: 4.86s Epoch: 2, Batch: 170/757, Loss: 0.5854, Time: 4.86s Epoch: 2, Batch: 180/757, Loss: 0.5781, Time: 4.87s Epoch: 2, Batch: 190/757, Loss: 0.5943, Time: 4.86s Epoch: 2, Batch: 200/757, Loss: 0.6070, Time: 4.86s Epoch: 2, Batch: 210/757, Loss: 0.2913, Time: 4.87s Epoch: 2, Batch: 220/757, Loss: 0.4581, Time: 4.86s Epoch: 2, Batch: 230/757, Loss: 0.6433, Time: 4.87s Epoch: 2, Batch: 240/757, Loss: 0.3878, Time: 4.88s Epoch: 2, Batch: 250/757, Loss: 0.6138, Time: 4.88s Epoch: 2, Batch: 260/757, Loss: 0.2756, Time: 4.88s Epoch: 2, Batch: 270/757, Loss: 0.9983, Time: 4.88s Epoch: 2, Batch: 280/757, Loss: 0.3467, Time: 4.87s Epoch: 2, Batch: 290/757, Loss: 0.3528, Time: 4.87s Epoch: 2, Batch: 300/757, Loss: 0.8320, Time: 4.87s Epoch: 2, Batch: 310/757, Loss: 0.8117, Time: 4.87s Epoch: 2, Batch: 320/757, Loss: 0.3243, Time: 4.87s Epoch: 2, Batch: 330/757, Loss: 0.3264, Time: 4.87s Epoch: 2, Batch: 340/757, Loss: 0.6325, Time: 4.87s Epoch: 2, Batch: 350/757, Loss: 0.7708, Time: 4.88s Epoch: 2, Batch: 360/757, Loss: 0.3129, Time: 4.87s Epoch: 2, Batch: 370/757, Loss: 0.9441, Time: 4.88s Epoch: 2, Batch: 380/757, Loss: 0.9134, Time: 4.88s Epoch: 2, Batch: 390/757, Loss: 0.5646, Time: 4.89s Epoch: 2, Batch: 400/757, Loss: 0.3808, Time: 4.89s Epoch: 2, Batch: 410/757, Loss: 0.6222, Time: 4.88s Epoch: 2, Batch: 420/757, Loss: 0.6120, Time: 4.88s Epoch: 2, Batch: 430/757, Loss: 0.9044, Time: 4.89s Epoch: 2, Batch: 440/757, Loss: 0.8404, Time: 4.88s Epoch: 2, Batch: 450/757, Loss: 1.1135, Time: 4.89s Epoch: 2, Batch: 460/757, Loss: 0.6810, Time: 4.89s Epoch: 2, Batch: 470/757, Loss: 0.7406, Time: 4.88s Epoch: 2, Batch: 480/757, Loss: 0.6562, Time: 4.88s Epoch: 2, Batch: 490/757, Loss: 0.3962, Time: 4.88s Epoch: 2, Batch: 500/757, Loss: 0.4655, Time: 4.88s Epoch: 2, Batch: 510/757, Loss: 0.5169, Time: 4.87s Epoch: 2, Batch: 520/757, Loss: 0.4278, Time: 4.88s Epoch: 2, Batch: 530/757, Loss: 0.7615, Time: 4.88s Epoch: 2, Batch: 540/757, Loss: 0.8216, Time: 4.87s Epoch: 2, Batch: 550/757, Loss: 0.4945, Time: 4.88s Epoch: 2, Batch: 560/757, Loss: 0.2919, Time: 4.88s Epoch: 2, Batch: 570/757, Loss: 0.7593, Time: 4.88s Epoch: 2, Batch: 580/757, Loss: 0.8451, Time: 4.88s Epoch: 2, Batch: 590/757, Loss: 0.5968, Time: 4.88s Epoch: 2, Batch: 600/757, Loss: 0.5975, Time: 4.88s Epoch: 2, Batch: 610/757, Loss: 0.5472, Time: 4.87s Epoch: 2, Batch: 620/757, Loss: 0.5334, Time: 4.87s Epoch: 2, Batch: 630/757, Loss: 0.5010, Time: 4.87s Epoch: 2, Batch: 640/757, Loss: 0.8547, Time: 4.87s Epoch: 2, Batch: 650/757, Loss: 0.3129, Time: 4.87s Epoch: 2, Batch: 660/757, Loss: 0.5059, Time: 4.86s Epoch: 2, Batch: 670/757, Loss: 0.7392, Time: 4.85s Epoch: 2, Batch: 680/757, Loss: 0.5843, Time: 4.85s Epoch: 2, Batch: 690/757, Loss: 0.4730, Time: 4.86s Epoch: 2, Batch: 700/757, Loss: 0.6370, Time: 4.86s Epoch: 2, Batch: 710/757, Loss: 0.4404, Time: 4.86s Epoch: 2, Batch: 720/757, Loss: 0.3192, Time: 4.86s Epoch: 2, Batch: 730/757, Loss: 0.3098, Time: 4.86s Epoch: 2, Batch: 740/757, Loss: 0.7573, Time: 4.86s Epoch: 2, Batch: 750/757, Loss: 0.5264, Time: 4.86s Epoch 3/20: Train Loss: 0.6151, Val Loss: 0.5932, Val IoU: 0.3150, Val Dice: 0.3509 Saving best model with IoU: 0.3150 Epoch: 3, Batch: 0/757, Loss: 1.1416, Time: 0.89s Epoch: 3, Batch: 10/757, Loss: 0.8220, Time: 4.86s Epoch: 3, Batch: 20/757, Loss: 0.6594, Time: 4.85s Epoch: 3, Batch: 30/757, Loss: 0.5261, Time: 4.85s Epoch: 3, Batch: 40/757, Loss: 0.8522, Time: 4.85s Epoch: 3, Batch: 50/757, Loss: 0.7730, Time: 4.85s Epoch: 3, Batch: 60/757, Loss: 0.5110, Time: 4.85s Epoch: 3, Batch: 70/757, Loss: 0.6732, Time: 4.86s Epoch: 3, Batch: 80/757, Loss: 0.7868, Time: 4.87s Epoch: 3, Batch: 90/757, Loss: 0.8388, Time: 4.87s Epoch: 3, Batch: 100/757, Loss: 0.6426, Time: 4.86s Epoch: 3, Batch: 110/757, Loss: 0.6824, Time: 4.86s Epoch: 3, Batch: 120/757, Loss: 0.5533, Time: 4.85s Epoch: 3, Batch: 130/757, Loss: 0.5501, Time: 4.85s Epoch: 3, Batch: 140/757, Loss: 0.2838, Time: 4.85s Epoch: 3, Batch: 150/757, Loss: 0.5047, Time: 4.85s Epoch: 3, Batch: 160/757, Loss: 0.3445, Time: 4.85s Epoch: 3, Batch: 170/757, Loss: 0.9574, Time: 4.86s Epoch: 3, Batch: 180/757, Loss: 0.3645, Time: 4.86s Epoch: 3, Batch: 190/757, Loss: 0.5933, Time: 4.86s Epoch: 3, Batch: 200/757, Loss: 0.5433, Time: 4.86s Epoch: 3, Batch: 210/757, Loss: 0.4577, Time: 4.86s Epoch: 3, Batch: 220/757, Loss: 0.4778, Time: 4.87s Epoch: 3, Batch: 230/757, Loss: 0.6035, Time: 4.87s Epoch: 3, Batch: 240/757, Loss: 0.3316, Time: 4.86s Epoch: 3, Batch: 250/757, Loss: 0.2873, Time: 4.86s Epoch: 3, Batch: 260/757, Loss: 0.9097, Time: 4.86s Epoch: 3, Batch: 270/757, Loss: 0.5571, Time: 4.86s Epoch: 3, Batch: 280/757, Loss: 0.4991, Time: 4.85s Epoch: 3, Batch: 290/757, Loss: 1.3256, Time: 4.85s Epoch: 3, Batch: 300/757, Loss: 0.4975, Time: 4.86s Epoch: 3, Batch: 310/757, Loss: 0.7547, Time: 4.86s Epoch: 3, Batch: 320/757, Loss: 0.6668, Time: 4.86s Epoch: 3, Batch: 330/757, Loss: 0.6834, Time: 4.86s Epoch: 3, Batch: 340/757, Loss: 0.7262, Time: 4.86s Epoch: 3, Batch: 350/757, Loss: 0.6545, Time: 4.86s Epoch: 3, Batch: 360/757, Loss: 1.2340, Time: 4.87s Epoch: 3, Batch: 370/757, Loss: 0.4834, Time: 4.87s Epoch: 3, Batch: 380/757, Loss: 0.3411, Time: 4.87s Epoch: 3, Batch: 390/757, Loss: 0.5282, Time: 4.86s Epoch: 3, Batch: 400/757, Loss: 0.9386, Time: 4.86s Epoch: 3, Batch: 410/757, Loss: 1.1112, Time: 4.86s Epoch: 3, Batch: 420/757, Loss: 0.7749, Time: 4.86s Epoch: 3, Batch: 430/757, Loss: 0.7374, Time: 4.85s Epoch: 3, Batch: 440/757, Loss: 0.5441, Time: 4.86s Epoch: 3, Batch: 450/757, Loss: 0.3293, Time: 4.86s Epoch: 3, Batch: 460/757, Loss: 0.2802, Time: 4.87s Epoch: 3, Batch: 470/757, Loss: 0.3111, Time: 4.87s Epoch: 3, Batch: 480/757, Loss: 0.3351, Time: 4.85s Epoch: 3, Batch: 490/757, Loss: 0.5260, Time: 4.86s Epoch: 3, Batch: 500/757, Loss: 0.7678, Time: 4.86s Epoch: 3, Batch: 510/757, Loss: 0.4742, Time: 4.86s Epoch: 3, Batch: 520/757, Loss: 0.6757, Time: 4.86s Epoch: 3, Batch: 530/757, Loss: 0.3425, Time: 4.85s Epoch: 3, Batch: 540/757, Loss: 0.5429, Time: 4.86s Epoch: 3, Batch: 550/757, Loss: 0.3459, Time: 4.85s Epoch: 3, Batch: 560/757, Loss: 0.6711, Time: 4.85s Epoch: 3, Batch: 570/757, Loss: 0.3993, Time: 4.85s Epoch: 3, Batch: 580/757, Loss: 0.3405, Time: 4.85s Epoch: 3, Batch: 590/757, Loss: 0.8175, Time: 4.85s Epoch: 3, Batch: 600/757, Loss: 1.5006, Time: 4.85s Epoch: 3, Batch: 610/757, Loss: 0.3850, Time: 4.86s Epoch: 3, Batch: 620/757, Loss: 0.6686, Time: 4.86s Epoch: 3, Batch: 630/757, Loss: 1.0451, Time: 4.85s Epoch: 3, Batch: 640/757, Loss: 0.5308, Time: 4.85s Epoch: 3, Batch: 650/757, Loss: 0.5119, Time: 4.85s Epoch: 3, Batch: 660/757, Loss: 0.6021, Time: 4.84s Epoch: 3, Batch: 670/757, Loss: 0.7448, Time: 4.85s Epoch: 3, Batch: 680/757, Loss: 0.4636, Time: 4.86s Epoch: 3, Batch: 690/757, Loss: 0.8495, Time: 4.85s Epoch: 3, Batch: 700/757, Loss: 0.9065, Time: 4.85s Epoch: 3, Batch: 710/757, Loss: 0.6727, Time: 4.85s Epoch: 3, Batch: 720/757, Loss: 0.3254, Time: 4.86s Epoch: 3, Batch: 730/757, Loss: 0.3344, Time: 4.86s Epoch: 3, Batch: 740/757, Loss: 0.5436, Time: 4.86s Epoch: 3, Batch: 750/757, Loss: 1.1337, Time: 4.85s Epoch 4/20: Train Loss: 0.5985, Val Loss: 0.6167, Val IoU: 0.3154, Val Dice: 0.3517 Saving best model with IoU: 0.3154 Epoch: 4, Batch: 0/757, Loss: 0.5212, Time: 0.89s Epoch: 4, Batch: 10/757, Loss: 0.5105, Time: 4.85s Epoch: 4, Batch: 20/757, Loss: 1.0858, Time: 4.85s Epoch: 4, Batch: 30/757, Loss: 0.6632, Time: 4.85s Epoch: 4, Batch: 40/757, Loss: 0.4489, Time: 4.85s Epoch: 4, Batch: 50/757, Loss: 0.6031, Time: 4.85s Epoch: 4, Batch: 60/757, Loss: 1.0699, Time: 4.85s Epoch: 4, Batch: 70/757, Loss: 0.5273, Time: 4.85s Epoch: 4, Batch: 80/757, Loss: 0.5466, Time: 4.85s Epoch: 4, Batch: 90/757, Loss: 0.5101, Time: 4.86s Epoch: 4, Batch: 100/757, Loss: 0.3616, Time: 4.86s Epoch: 4, Batch: 110/757, Loss: 0.6796, Time: 4.87s Epoch: 4, Batch: 120/757, Loss: 0.4327, Time: 4.86s Epoch: 4, Batch: 130/757, Loss: 0.5884, Time: 4.86s Epoch: 4, Batch: 140/757, Loss: 0.4815, Time: 4.86s Epoch: 4, Batch: 150/757, Loss: 0.5405, Time: 4.84s Epoch: 4, Batch: 160/757, Loss: 0.8143, Time: 4.85s Epoch: 4, Batch: 170/757, Loss: 0.5924, Time: 4.84s Epoch: 4, Batch: 180/757, Loss: 0.4630, Time: 4.84s Epoch: 4, Batch: 190/757, Loss: 0.5618, Time: 4.84s Epoch: 4, Batch: 200/757, Loss: 0.8115, Time: 4.83s Epoch: 4, Batch: 210/757, Loss: 0.2620, Time: 4.84s Epoch: 4, Batch: 220/757, Loss: 0.2407, Time: 4.84s Epoch: 4, Batch: 230/757, Loss: 0.4861, Time: 4.84s Epoch: 4, Batch: 240/757, Loss: 0.5772, Time: 4.84s Epoch: 4, Batch: 250/757, Loss: 0.7051, Time: 4.84s Epoch: 4, Batch: 260/757, Loss: 1.0942, Time: 4.84s Epoch: 4, Batch: 270/757, Loss: 0.3087, Time: 4.83s Epoch: 4, Batch: 280/757, Loss: 0.7904, Time: 4.84s Epoch: 4, Batch: 290/757, Loss: 0.5296, Time: 4.84s Epoch: 4, Batch: 300/757, Loss: 0.5682, Time: 4.84s Epoch: 4, Batch: 310/757, Loss: 0.2934, Time: 4.83s Epoch: 4, Batch: 320/757, Loss: 0.7254, Time: 4.84s Epoch: 4, Batch: 330/757, Loss: 0.5265, Time: 4.84s Epoch: 4, Batch: 340/757, Loss: 0.5184, Time: 4.84s Epoch: 4, Batch: 350/757, Loss: 0.6322, Time: 4.85s Epoch: 4, Batch: 360/757, Loss: 0.5239, Time: 4.84s Epoch: 4, Batch: 370/757, Loss: 0.8933, Time: 4.84s Epoch: 4, Batch: 380/757, Loss: 0.6705, Time: 4.84s Epoch: 4, Batch: 390/757, Loss: 0.3275, Time: 4.84s Epoch: 4, Batch: 400/757, Loss: 1.0026, Time: 4.85s Epoch: 4, Batch: 410/757, Loss: 0.7060, Time: 4.85s Epoch: 4, Batch: 420/757, Loss: 0.6047, Time: 4.85s Epoch: 4, Batch: 430/757, Loss: 0.5646, Time: 4.84s Epoch: 4, Batch: 440/757, Loss: 0.2617, Time: 4.85s Epoch: 4, Batch: 450/757, Loss: 0.6035, Time: 4.85s Epoch: 4, Batch: 460/757, Loss: 0.5296, Time: 4.84s Epoch: 4, Batch: 470/757, Loss: 0.2977, Time: 4.83s Epoch: 4, Batch: 480/757, Loss: 0.6466, Time: 4.84s Epoch: 4, Batch: 490/757, Loss: 0.3570, Time: 4.84s Epoch: 4, Batch: 500/757, Loss: 1.0000, Time: 4.84s Epoch: 4, Batch: 510/757, Loss: 0.5589, Time: 4.83s Epoch: 4, Batch: 520/757, Loss: 0.4279, Time: 4.83s Epoch: 4, Batch: 530/757, Loss: 0.3961, Time: 4.84s Epoch: 4, Batch: 540/757, Loss: 0.4845, Time: 4.84s Epoch: 4, Batch: 550/757, Loss: 0.4925, Time: 4.83s Epoch: 4, Batch: 560/757, Loss: 0.7184, Time: 4.82s Epoch: 4, Batch: 570/757, Loss: 0.4381, Time: 4.83s Epoch: 4, Batch: 580/757, Loss: 0.7860, Time: 4.83s Epoch: 4, Batch: 590/757, Loss: 0.6765, Time: 4.83s Epoch: 4, Batch: 600/757, Loss: 0.3623, Time: 4.83s Epoch: 4, Batch: 610/757, Loss: 0.6059, Time: 4.83s Epoch: 4, Batch: 620/757, Loss: 0.6299, Time: 4.83s Epoch: 4, Batch: 630/757, Loss: 0.5980, Time: 4.83s Epoch: 4, Batch: 640/757, Loss: 0.6087, Time: 4.83s Epoch: 4, Batch: 650/757, Loss: 0.8919, Time: 4.83s Epoch: 4, Batch: 660/757, Loss: 0.5647, Time: 4.83s Epoch: 4, Batch: 670/757, Loss: 0.5683, Time: 4.83s Epoch: 4, Batch: 680/757, Loss: 0.7472, Time: 4.83s Epoch: 4, Batch: 690/757, Loss: 0.5906, Time: 4.83s Epoch: 4, Batch: 700/757, Loss: 0.3668, Time: 4.84s Epoch: 4, Batch: 710/757, Loss: 0.3667, Time: 4.83s Epoch: 4, Batch: 720/757, Loss: 0.6340, Time: 4.83s Epoch: 4, Batch: 730/757, Loss: 0.3891, Time: 4.83s Epoch: 4, Batch: 740/757, Loss: 0.4604, Time: 4.83s Epoch: 4, Batch: 750/757, Loss: 0.3916, Time: 4.83s Epoch 5/20: Train Loss: 0.5878, Val Loss: 0.5857, Val IoU: 0.3320, Val Dice: 0.3715 Saving best model with IoU: 0.3320 Epoch: 5, Batch: 0/757, Loss: 0.6138, Time: 0.84s Epoch: 5, Batch: 10/757, Loss: 0.6239, Time: 4.81s Epoch: 5, Batch: 20/757, Loss: 0.2985, Time: 4.82s Epoch: 5, Batch: 30/757, Loss: 0.6213, Time: 4.82s Epoch: 5, Batch: 40/757, Loss: 0.4083, Time: 4.82s Epoch: 5, Batch: 50/757, Loss: 0.5536, Time: 4.81s Epoch: 5, Batch: 60/757, Loss: 0.3910, Time: 4.81s Epoch: 5, Batch: 70/757, Loss: 0.8001, Time: 4.82s Epoch: 5, Batch: 80/757, Loss: 0.3575, Time: 4.81s Epoch: 5, Batch: 90/757, Loss: 0.9363, Time: 4.82s Epoch: 5, Batch: 100/757, Loss: 0.5621, Time: 4.82s Epoch: 5, Batch: 110/757, Loss: 0.7214, Time: 4.82s Epoch: 5, Batch: 120/757, Loss: 0.4454, Time: 4.82s Epoch: 5, Batch: 130/757, Loss: 0.6043, Time: 4.82s Epoch: 5, Batch: 140/757, Loss: 0.4629, Time: 4.81s Epoch: 5, Batch: 150/757, Loss: 0.8554, Time: 4.82s Epoch: 5, Batch: 160/757, Loss: 0.5396, Time: 4.82s Epoch: 5, Batch: 170/757, Loss: 0.2859, Time: 4.82s Epoch: 5, Batch: 180/757, Loss: 0.6801, Time: 4.82s Epoch: 5, Batch: 190/757, Loss: 0.4582, Time: 4.82s Epoch: 5, Batch: 200/757, Loss: 0.6820, Time: 4.83s Epoch: 5, Batch: 210/757, Loss: 0.6862, Time: 4.82s Epoch: 5, Batch: 220/757, Loss: 0.7667, Time: 4.82s Epoch: 5, Batch: 230/757, Loss: 0.6028, Time: 4.82s Epoch: 5, Batch: 240/757, Loss: 0.7692, Time: 4.82s Epoch: 5, Batch: 250/757, Loss: 0.3122, Time: 4.81s Epoch: 5, Batch: 260/757, Loss: 0.2030, Time: 4.82s Epoch: 5, Batch: 270/757, Loss: 0.4182, Time: 4.81s Epoch: 5, Batch: 280/757, Loss: 0.6088, Time: 4.81s Epoch: 5, Batch: 290/757, Loss: 0.5867, Time: 4.81s Epoch: 5, Batch: 300/757, Loss: 0.7849, Time: 4.82s Epoch: 5, Batch: 310/757, Loss: 0.5269, Time: 4.81s Epoch: 5, Batch: 320/757, Loss: 0.4480, Time: 4.82s Epoch: 5, Batch: 330/757, Loss: 0.5539, Time: 4.82s Epoch: 5, Batch: 340/757, Loss: 0.4366, Time: 4.82s Epoch: 5, Batch: 350/757, Loss: 0.4167, Time: 4.81s Epoch: 5, Batch: 360/757, Loss: 0.6181, Time: 4.82s Epoch: 5, Batch: 370/757, Loss: 0.6924, Time: 4.81s Epoch: 5, Batch: 380/757, Loss: 0.4851, Time: 4.82s Epoch: 5, Batch: 390/757, Loss: 0.5519, Time: 4.82s Epoch: 5, Batch: 400/757, Loss: 0.5793, Time: 4.82s Epoch: 5, Batch: 410/757, Loss: 0.7086, Time: 4.82s Epoch: 5, Batch: 420/757, Loss: 0.5298, Time: 4.82s Epoch: 5, Batch: 430/757, Loss: 0.4963, Time: 4.82s Epoch: 5, Batch: 440/757, Loss: 0.5407, Time: 4.82s Epoch: 5, Batch: 450/757, Loss: 0.4871, Time: 4.82s Epoch: 5, Batch: 460/757, Loss: 0.2827, Time: 4.82s Epoch: 5, Batch: 470/757, Loss: 0.6225, Time: 4.81s Epoch: 5, Batch: 480/757, Loss: 1.0804, Time: 4.82s Epoch: 5, Batch: 490/757, Loss: 0.3578, Time: 4.81s Epoch: 5, Batch: 500/757, Loss: 0.6160, Time: 4.81s Epoch: 5, Batch: 510/757, Loss: 0.5207, Time: 4.81s Epoch: 5, Batch: 520/757, Loss: 0.3649, Time: 4.81s Epoch: 5, Batch: 530/757, Loss: 0.3148, Time: 4.82s Epoch: 5, Batch: 540/757, Loss: 0.9040, Time: 4.81s Epoch: 5, Batch: 550/757, Loss: 0.7492, Time: 4.81s Epoch: 5, Batch: 560/757, Loss: 0.7655, Time: 4.81s Epoch: 5, Batch: 570/757, Loss: 0.5509, Time: 4.81s Epoch: 5, Batch: 580/757, Loss: 0.6091, Time: 4.81s Epoch: 5, Batch: 590/757, Loss: 0.7188, Time: 4.81s Epoch: 5, Batch: 600/757, Loss: 0.4752, Time: 4.81s Epoch: 5, Batch: 610/757, Loss: 0.8159, Time: 4.81s Epoch: 5, Batch: 620/757, Loss: 0.8069, Time: 4.81s Epoch: 5, Batch: 630/757, Loss: 0.6037, Time: 4.81s Epoch: 5, Batch: 640/757, Loss: 0.4252, Time: 4.81s Epoch: 5, Batch: 650/757, Loss: 0.2629, Time: 4.81s Epoch: 5, Batch: 660/757, Loss: 0.8482, Time: 4.81s Epoch: 5, Batch: 670/757, Loss: 0.6947, Time: 4.81s Epoch: 5, Batch: 680/757, Loss: 0.8552, Time: 4.81s Epoch: 5, Batch: 690/757, Loss: 0.8914, Time: 4.81s Epoch: 5, Batch: 700/757, Loss: 0.4127, Time: 4.81s Epoch: 5, Batch: 710/757, Loss: 0.8171, Time: 4.81s Epoch: 5, Batch: 720/757, Loss: 0.4508, Time: 4.81s Epoch: 5, Batch: 730/757, Loss: 0.2936, Time: 4.81s Epoch: 5, Batch: 740/757, Loss: 0.8161, Time: 4.81s Epoch: 5, Batch: 750/757, Loss: 0.8177, Time: 4.81s Epoch 6/20: Train Loss: 0.5754, Val Loss: 0.5674, Val IoU: 0.3355, Val Dice: 0.3747 Saving best model with IoU: 0.3355 Epoch: 6, Batch: 0/757, Loss: 0.4922, Time: 0.89s Epoch: 6, Batch: 10/757, Loss: 0.9334, Time: 4.80s Epoch: 6, Batch: 20/757, Loss: 0.6642, Time: 4.80s Epoch: 6, Batch: 30/757, Loss: 1.1808, Time: 4.79s Epoch: 6, Batch: 40/757, Loss: 0.3606, Time: 4.80s Epoch: 6, Batch: 50/757, Loss: 0.4907, Time: 4.80s Epoch: 6, Batch: 60/757, Loss: 0.5083, Time: 4.80s Epoch: 6, Batch: 70/757, Loss: 0.3759, Time: 4.80s Epoch: 6, Batch: 80/757, Loss: 0.3107, Time: 4.80s Epoch: 6, Batch: 90/757, Loss: 1.3929, Time: 4.79s Epoch: 6, Batch: 100/757, Loss: 0.8224, Time: 4.80s Epoch: 6, Batch: 110/757, Loss: 0.4163, Time: 4.80s Epoch: 6, Batch: 120/757, Loss: 0.4020, Time: 4.79s Epoch: 6, Batch: 130/757, Loss: 0.6965, Time: 4.80s Epoch: 6, Batch: 140/757, Loss: 0.5320, Time: 4.80s Epoch: 6, Batch: 150/757, Loss: 0.7760, Time: 4.79s Epoch: 6, Batch: 160/757, Loss: 0.4805, Time: 4.79s Epoch: 6, Batch: 170/757, Loss: 0.6905, Time: 4.79s Epoch: 6, Batch: 180/757, Loss: 0.8068, Time: 4.80s Epoch: 6, Batch: 190/757, Loss: 0.3143, Time: 4.79s Epoch: 6, Batch: 200/757, Loss: 0.2513, Time: 4.79s Epoch: 6, Batch: 210/757, Loss: 0.4933, Time: 4.79s Epoch: 6, Batch: 220/757, Loss: 0.7793, Time: 4.79s Epoch: 6, Batch: 230/757, Loss: 0.8277, Time: 4.79s Epoch: 6, Batch: 240/757, Loss: 0.6571, Time: 4.79s Epoch: 6, Batch: 250/757, Loss: 0.7181, Time: 4.79s Epoch: 6, Batch: 260/757, Loss: 0.6721, Time: 4.79s Epoch: 6, Batch: 270/757, Loss: 0.6787, Time: 4.79s Epoch: 6, Batch: 280/757, Loss: 0.6038, Time: 4.79s Epoch: 6, Batch: 290/757, Loss: 0.4594, Time: 4.79s Epoch: 6, Batch: 300/757, Loss: 0.3141, Time: 4.79s Epoch: 6, Batch: 310/757, Loss: 0.6055, Time: 4.79s Epoch: 6, Batch: 320/757, Loss: 0.6325, Time: 4.80s Epoch: 6, Batch: 330/757, Loss: 0.2866, Time: 4.80s Epoch: 6, Batch: 340/757, Loss: 0.5243, Time: 4.79s Epoch: 6, Batch: 350/757, Loss: 0.4850, Time: 4.80s Epoch: 6, Batch: 360/757, Loss: 0.8631, Time: 4.80s Epoch: 6, Batch: 370/757, Loss: 0.3126, Time: 4.79s Epoch: 6, Batch: 380/757, Loss: 0.6113, Time: 4.80s Epoch: 6, Batch: 390/757, Loss: 0.2743, Time: 4.80s Epoch: 6, Batch: 400/757, Loss: 0.3334, Time: 4.80s Epoch: 6, Batch: 410/757, Loss: 0.6077, Time: 4.79s Epoch: 6, Batch: 420/757, Loss: 0.7946, Time: 4.79s Epoch: 6, Batch: 430/757, Loss: 0.7388, Time: 4.79s Epoch: 6, Batch: 440/757, Loss: 0.4934, Time: 4.79s Epoch: 6, Batch: 450/757, Loss: 0.7040, Time: 4.78s Epoch: 6, Batch: 460/757, Loss: 0.7335, Time: 4.78s Epoch: 6, Batch: 470/757, Loss: 0.4929, Time: 4.79s Epoch: 6, Batch: 480/757, Loss: 0.6388, Time: 4.79s Epoch: 6, Batch: 490/757, Loss: 0.9563, Time: 4.79s Epoch: 6, Batch: 500/757, Loss: 0.3171, Time: 4.78s Epoch: 6, Batch: 510/757, Loss: 0.8840, Time: 4.78s Epoch: 6, Batch: 520/757, Loss: 0.9089, Time: 4.79s Epoch: 6, Batch: 530/757, Loss: 0.5365, Time: 4.79s Epoch: 6, Batch: 540/757, Loss: 0.9408, Time: 4.78s Epoch: 6, Batch: 550/757, Loss: 0.3894, Time: 4.79s Epoch: 6, Batch: 560/757, Loss: 0.4718, Time: 4.79s Epoch: 6, Batch: 570/757, Loss: 0.4568, Time: 4.78s Epoch: 6, Batch: 580/757, Loss: 0.3641, Time: 4.78s Epoch: 6, Batch: 590/757, Loss: 0.3494, Time: 4.79s Epoch: 6, Batch: 600/757, Loss: 0.3085, Time: 4.79s Epoch: 6, Batch: 610/757, Loss: 0.3885, Time: 4.79s Epoch: 6, Batch: 620/757, Loss: 0.7463, Time: 4.79s Epoch: 6, Batch: 630/757, Loss: 0.7439, Time: 4.78s Epoch: 6, Batch: 640/757, Loss: 0.4855, Time: 4.79s Epoch: 6, Batch: 650/757, Loss: 0.8113, Time: 4.79s Epoch: 6, Batch: 660/757, Loss: 0.4732, Time: 4.79s Epoch: 6, Batch: 670/757, Loss: 0.5120, Time: 4.79s Epoch: 6, Batch: 680/757, Loss: 0.8537, Time: 4.79s Epoch: 6, Batch: 690/757, Loss: 0.2928, Time: 4.79s Epoch: 6, Batch: 700/757, Loss: 0.4544, Time: 4.79s Epoch: 6, Batch: 710/757, Loss: 0.4319, Time: 4.79s Epoch: 6, Batch: 720/757, Loss: 0.5356, Time: 4.79s Epoch: 6, Batch: 730/757, Loss: 0.5955, Time: 4.79s Epoch: 6, Batch: 740/757, Loss: 0.5015, Time: 4.78s Epoch: 6, Batch: 750/757, Loss: 0.6271, Time: 4.78s Epoch 7/20: Train Loss: 0.5712, Val Loss: 0.5863, Val IoU: 0.3350, Val Dice: 0.3740 Epoch: 7, Batch: 0/757, Loss: 0.3359, Time: 0.82s Epoch: 7, Batch: 10/757, Loss: 0.6134, Time: 4.76s Epoch: 7, Batch: 20/757, Loss: 0.5640, Time: 4.76s Epoch: 7, Batch: 30/757, Loss: 0.7456, Time: 4.77s Epoch: 7, Batch: 40/757, Loss: 0.4894, Time: 4.77s Epoch: 7, Batch: 50/757, Loss: 0.2763, Time: 4.76s Epoch: 7, Batch: 60/757, Loss: 0.4607, Time: 4.76s Epoch: 7, Batch: 70/757, Loss: 0.6823, Time: 4.77s Epoch: 7, Batch: 80/757, Loss: 0.3634, Time: 4.77s Epoch: 7, Batch: 90/757, Loss: 0.3294, Time: 4.77s Epoch: 7, Batch: 100/757, Loss: 1.0374, Time: 4.78s Epoch: 7, Batch: 110/757, Loss: 0.5924, Time: 4.78s Epoch: 7, Batch: 120/757, Loss: 0.9425, Time: 4.78s Epoch: 7, Batch: 130/757, Loss: 0.3786, Time: 4.78s Epoch: 7, Batch: 140/757, Loss: 0.4786, Time: 4.78s Epoch: 7, Batch: 150/757, Loss: 0.5065, Time: 4.78s Epoch: 7, Batch: 160/757, Loss: 0.2638, Time: 4.79s Epoch: 7, Batch: 170/757, Loss: 0.9543, Time: 4.78s Epoch: 7, Batch: 180/757, Loss: 0.6087, Time: 4.78s Epoch: 7, Batch: 190/757, Loss: 0.3728, Time: 4.78s Epoch: 7, Batch: 200/757, Loss: 0.7498, Time: 4.78s Epoch: 7, Batch: 210/757, Loss: 0.6074, Time: 4.78s Epoch: 7, Batch: 220/757, Loss: 0.3653, Time: 4.77s Epoch: 7, Batch: 230/757, Loss: 0.4777, Time: 4.77s Epoch: 7, Batch: 240/757, Loss: 0.3814, Time: 4.76s Epoch: 7, Batch: 250/757, Loss: 0.5578, Time: 4.76s Epoch: 7, Batch: 260/757, Loss: 1.0481, Time: 4.76s Epoch: 7, Batch: 270/757, Loss: 1.4195, Time: 4.77s Epoch: 7, Batch: 280/757, Loss: 0.5418, Time: 4.77s Epoch: 7, Batch: 290/757, Loss: 0.2711, Time: 4.75s Epoch: 7, Batch: 300/757, Loss: 0.4881, Time: 4.76s Epoch: 7, Batch: 310/757, Loss: 0.6858, Time: 4.77s Epoch: 7, Batch: 320/757, Loss: 0.4167, Time: 4.76s Epoch: 7, Batch: 330/757, Loss: 0.4871, Time: 4.77s Epoch: 7, Batch: 340/757, Loss: 0.3816, Time: 4.77s Epoch: 7, Batch: 350/757, Loss: 0.5283, Time: 4.76s Epoch: 7, Batch: 360/757, Loss: 0.8637, Time: 4.77s Epoch: 7, Batch: 370/757, Loss: 0.4810, Time: 4.76s Epoch: 7, Batch: 380/757, Loss: 0.2589, Time: 4.76s Epoch: 7, Batch: 390/757, Loss: 0.4637, Time: 4.76s Epoch: 7, Batch: 400/757, Loss: 0.7449, Time: 4.76s Epoch: 7, Batch: 410/757, Loss: 0.4510, Time: 4.77s Epoch: 7, Batch: 420/757, Loss: 0.3775, Time: 4.77s Epoch: 7, Batch: 430/757, Loss: 0.2962, Time: 4.76s Epoch: 7, Batch: 440/757, Loss: 0.5094, Time: 4.77s Epoch: 7, Batch: 450/757, Loss: 0.5706, Time: 4.77s Epoch: 7, Batch: 460/757, Loss: 0.6249, Time: 4.77s Epoch: 7, Batch: 470/757, Loss: 0.7427, Time: 4.77s Epoch: 7, Batch: 480/757, Loss: 0.5383, Time: 4.77s Epoch: 7, Batch: 490/757, Loss: 0.7270, Time: 4.77s Epoch: 7, Batch: 500/757, Loss: 0.5682, Time: 4.77s Epoch: 7, Batch: 510/757, Loss: 0.3378, Time: 4.77s Epoch: 7, Batch: 520/757, Loss: 0.4694, Time: 4.78s Epoch: 7, Batch: 530/757, Loss: 0.4145, Time: 4.78s Epoch: 7, Batch: 540/757, Loss: 0.3081, Time: 4.77s Epoch: 7, Batch: 550/757, Loss: 0.5910, Time: 4.78s Epoch: 7, Batch: 560/757, Loss: 0.8589, Time: 4.77s Epoch: 7, Batch: 570/757, Loss: 0.6880, Time: 4.77s Epoch: 7, Batch: 580/757, Loss: 0.8790, Time: 4.77s Epoch: 7, Batch: 590/757, Loss: 0.4845, Time: 4.77s Epoch: 7, Batch: 600/757, Loss: 0.3195, Time: 4.77s Epoch: 7, Batch: 610/757, Loss: 0.3662, Time: 4.76s Epoch: 7, Batch: 620/757, Loss: 0.7964, Time: 4.77s Epoch: 7, Batch: 630/757, Loss: 0.8406, Time: 4.76s Epoch: 7, Batch: 640/757, Loss: 0.4906, Time: 4.77s Epoch: 7, Batch: 650/757, Loss: 0.4535, Time: 4.76s Epoch: 7, Batch: 660/757, Loss: 0.7009, Time: 4.76s Epoch: 7, Batch: 670/757, Loss: 0.4227, Time: 4.76s Epoch: 7, Batch: 680/757, Loss: 0.4174, Time: 4.76s Epoch: 7, Batch: 690/757, Loss: 0.6852, Time: 4.76s Epoch: 7, Batch: 700/757, Loss: 0.2897, Time: 4.76s Epoch: 7, Batch: 710/757, Loss: 0.3016, Time: 4.75s Epoch: 7, Batch: 720/757, Loss: 0.4465, Time: 4.76s Epoch: 7, Batch: 730/757, Loss: 0.5089, Time: 4.76s Epoch: 7, Batch: 740/757, Loss: 0.4395, Time: 4.75s Epoch: 7, Batch: 750/757, Loss: 0.6072, Time: 4.76s Epoch 8/20: Train Loss: 0.5602, Val Loss: 0.5441, Val IoU: 0.3194, Val Dice: 0.3573 Epoch: 8, Batch: 0/757, Loss: 0.3868, Time: 0.82s Epoch: 8, Batch: 10/757, Loss: 0.2865, Time: 4.76s Epoch: 8, Batch: 20/757, Loss: 0.5458, Time: 4.75s Epoch: 8, Batch: 30/757, Loss: 0.4367, Time: 4.76s Epoch: 8, Batch: 40/757, Loss: 0.6564, Time: 4.76s Epoch: 8, Batch: 50/757, Loss: 0.3470, Time: 4.76s Epoch: 8, Batch: 60/757, Loss: 0.3446, Time: 4.76s Epoch: 8, Batch: 70/757, Loss: 0.7714, Time: 4.75s Epoch: 8, Batch: 80/757, Loss: 0.7958, Time: 4.76s Epoch: 8, Batch: 90/757, Loss: 0.3360, Time: 4.75s Epoch: 8, Batch: 100/757, Loss: 0.4694, Time: 4.75s Epoch: 8, Batch: 110/757, Loss: 0.5351, Time: 4.76s Epoch: 8, Batch: 120/757, Loss: 0.8098, Time: 4.76s Epoch: 8, Batch: 130/757, Loss: 0.3915, Time: 4.76s Epoch: 8, Batch: 140/757, Loss: 0.6932, Time: 4.76s Epoch: 8, Batch: 150/757, Loss: 0.4918, Time: 4.76s Epoch: 8, Batch: 160/757, Loss: 0.3696, Time: 4.76s Epoch: 8, Batch: 170/757, Loss: 0.5286, Time: 4.76s Epoch: 8, Batch: 180/757, Loss: 0.4616, Time: 4.76s Epoch: 8, Batch: 190/757, Loss: 0.3392, Time: 4.76s Epoch: 8, Batch: 200/757, Loss: 0.2839, Time: 4.76s Epoch: 8, Batch: 210/757, Loss: 0.3168, Time: 4.76s Epoch: 8, Batch: 220/757, Loss: 0.5922, Time: 4.76s Epoch: 8, Batch: 230/757, Loss: 0.3709, Time: 4.76s Epoch: 8, Batch: 240/757, Loss: 0.4285, Time: 4.75s Epoch: 8, Batch: 250/757, Loss: 0.9365, Time: 4.75s Epoch: 8, Batch: 260/757, Loss: 0.3042, Time: 4.75s Epoch: 8, Batch: 270/757, Loss: 0.6342, Time: 4.76s Epoch: 8, Batch: 280/757, Loss: 0.5357, Time: 4.76s Epoch: 8, Batch: 290/757, Loss: 0.6527, Time: 4.75s Epoch: 8, Batch: 300/757, Loss: 0.6145, Time: 4.76s Epoch: 8, Batch: 310/757, Loss: 0.5933, Time: 4.76s Epoch: 8, Batch: 320/757, Loss: 0.5348, Time: 4.75s Epoch: 8, Batch: 330/757, Loss: 0.7419, Time: 4.75s Epoch: 8, Batch: 340/757, Loss: 0.4995, Time: 4.75s Epoch: 8, Batch: 350/757, Loss: 0.5305, Time: 4.76s Epoch: 8, Batch: 360/757, Loss: 0.2861, Time: 4.75s Epoch: 8, Batch: 370/757, Loss: 0.6960, Time: 4.76s Epoch: 8, Batch: 380/757, Loss: 0.5514, Time: 4.75s Epoch: 8, Batch: 390/757, Loss: 1.1289, Time: 4.75s Epoch: 8, Batch: 400/757, Loss: 0.5055, Time: 4.75s Epoch: 8, Batch: 410/757, Loss: 0.4796, Time: 4.75s Epoch: 8, Batch: 420/757, Loss: 0.8009, Time: 4.75s Epoch: 8, Batch: 430/757, Loss: 0.6813, Time: 4.76s Epoch: 8, Batch: 440/757, Loss: 0.6740, Time: 4.76s Epoch: 8, Batch: 450/757, Loss: 0.7439, Time: 4.75s Epoch: 8, Batch: 460/757, Loss: 0.4253, Time: 4.74s Epoch: 8, Batch: 470/757, Loss: 0.7624, Time: 4.75s Epoch: 8, Batch: 480/757, Loss: 0.3262, Time: 4.75s Epoch: 8, Batch: 490/757, Loss: 0.5891, Time: 4.75s Epoch: 8, Batch: 500/757, Loss: 0.4150, Time: 4.75s Epoch: 8, Batch: 510/757, Loss: 0.7605, Time: 4.75s Epoch: 8, Batch: 520/757, Loss: 0.6922, Time: 4.75s Epoch: 8, Batch: 530/757, Loss: 0.7411, Time: 4.75s Epoch: 8, Batch: 540/757, Loss: 0.5026, Time: 4.75s Epoch: 8, Batch: 550/757, Loss: 0.4680, Time: 4.74s Epoch: 8, Batch: 560/757, Loss: 0.3645, Time: 4.75s Epoch: 8, Batch: 570/757, Loss: 0.3215, Time: 4.74s Epoch: 8, Batch: 580/757, Loss: 0.3296, Time: 4.75s Epoch: 8, Batch: 590/757, Loss: 0.3480, Time: 4.75s Epoch: 8, Batch: 600/757, Loss: 1.0730, Time: 4.74s Epoch: 8, Batch: 610/757, Loss: 0.7550, Time: 4.74s Epoch: 8, Batch: 620/757, Loss: 0.2892, Time: 4.74s Epoch: 8, Batch: 630/757, Loss: 0.3223, Time: 4.74s Epoch: 8, Batch: 640/757, Loss: 0.4850, Time: 4.75s Epoch: 8, Batch: 650/757, Loss: 0.5510, Time: 4.75s Epoch: 8, Batch: 660/757, Loss: 0.7235, Time: 4.75s Epoch: 8, Batch: 670/757, Loss: 0.5867, Time: 4.76s Epoch: 8, Batch: 680/757, Loss: 0.5838, Time: 4.75s Epoch: 8, Batch: 690/757, Loss: 0.5890, Time: 4.75s Epoch: 8, Batch: 700/757, Loss: 0.3850, Time: 4.75s Epoch: 8, Batch: 710/757, Loss: 0.3619, Time: 4.75s Epoch: 8, Batch: 720/757, Loss: 0.7793, Time: 4.75s Epoch: 8, Batch: 730/757, Loss: 0.2863, Time: 4.75s Epoch: 8, Batch: 740/757, Loss: 0.4721, Time: 4.76s Epoch: 8, Batch: 750/757, Loss: 0.5128, Time: 4.76s Epoch 9/20: Train Loss: 0.5514, Val Loss: 0.6277, Val IoU: 0.3268, Val Dice: 0.3683 Epoch: 9, Batch: 0/757, Loss: 0.4566, Time: 0.86s Epoch: 9, Batch: 10/757, Loss: 0.2563, Time: 4.74s Epoch: 9, Batch: 20/757, Loss: 0.3855, Time: 4.73s Epoch: 9, Batch: 30/757, Loss: 1.1399, Time: 4.73s Epoch: 9, Batch: 40/757, Loss: 0.5954, Time: 4.73s Epoch: 9, Batch: 50/757, Loss: 0.8147, Time: 4.73s Epoch: 9, Batch: 60/757, Loss: 0.3863, Time: 4.73s Epoch: 9, Batch: 70/757, Loss: 0.4843, Time: 4.73s Epoch: 9, Batch: 80/757, Loss: 0.7824, Time: 4.73s Epoch: 9, Batch: 90/757, Loss: 0.4750, Time: 4.74s Epoch: 9, Batch: 100/757, Loss: 0.8625, Time: 4.74s Epoch: 9, Batch: 110/757, Loss: 0.9204, Time: 4.74s Epoch: 9, Batch: 120/757, Loss: 0.4026, Time: 4.75s Epoch: 9, Batch: 130/757, Loss: 0.5753, Time: 4.74s Epoch: 9, Batch: 140/757, Loss: 0.3721, Time: 4.75s Epoch: 9, Batch: 150/757, Loss: 1.0693, Time: 4.75s Epoch: 9, Batch: 160/757, Loss: 0.8737, Time: 4.75s Epoch: 9, Batch: 170/757, Loss: 0.4910, Time: 4.75s Epoch: 9, Batch: 180/757, Loss: 0.5364, Time: 4.75s Epoch: 9, Batch: 190/757, Loss: 0.4325, Time: 4.75s Epoch: 9, Batch: 200/757, Loss: 0.5491, Time: 4.76s Epoch: 9, Batch: 210/757, Loss: 0.5551, Time: 4.75s Epoch: 9, Batch: 220/757, Loss: 0.3001, Time: 4.75s Epoch: 9, Batch: 230/757, Loss: 0.4316, Time: 4.74s Epoch: 9, Batch: 240/757, Loss: 0.6573, Time: 4.74s Epoch: 9, Batch: 250/757, Loss: 0.8299, Time: 4.74s Epoch: 9, Batch: 260/757, Loss: 0.5130, Time: 4.74s Epoch: 9, Batch: 270/757, Loss: 0.5151, Time: 4.74s Epoch: 9, Batch: 280/757, Loss: 0.9298, Time: 4.73s Epoch: 9, Batch: 290/757, Loss: 0.3831, Time: 4.73s Epoch: 9, Batch: 300/757, Loss: 1.3051, Time: 4.73s Epoch: 9, Batch: 310/757, Loss: 0.4325, Time: 4.73s Epoch: 9, Batch: 320/757, Loss: 0.4671, Time: 4.73s Epoch: 9, Batch: 330/757, Loss: 0.4807, Time: 4.73s Epoch: 9, Batch: 340/757, Loss: 0.6159, Time: 4.73s Epoch: 9, Batch: 350/757, Loss: 0.7449, Time: 4.73s Epoch: 9, Batch: 360/757, Loss: 1.1293, Time: 4.73s Epoch: 9, Batch: 370/757, Loss: 0.7798, Time: 4.73s Epoch: 9, Batch: 380/757, Loss: 0.2912, Time: 4.74s Epoch: 9, Batch: 390/757, Loss: 1.0740, Time: 4.74s Epoch: 9, Batch: 400/757, Loss: 0.5289, Time: 4.74s Epoch: 9, Batch: 410/757, Loss: 0.5621, Time: 4.75s Epoch: 9, Batch: 420/757, Loss: 0.4504, Time: 4.75s Epoch: 9, Batch: 430/757, Loss: 0.2517, Time: 4.75s Epoch: 9, Batch: 440/757, Loss: 0.3759, Time: 4.75s Epoch: 9, Batch: 450/757, Loss: 0.5703, Time: 4.74s Epoch: 9, Batch: 460/757, Loss: 0.3714, Time: 4.75s Epoch: 9, Batch: 470/757, Loss: 0.5667, Time: 4.75s Epoch: 9, Batch: 480/757, Loss: 0.5174, Time: 4.74s Epoch: 9, Batch: 490/757, Loss: 0.4274, Time: 4.74s Epoch: 9, Batch: 500/757, Loss: 0.4091, Time: 4.75s Epoch: 9, Batch: 510/757, Loss: 0.3374, Time: 4.75s Epoch: 9, Batch: 520/757, Loss: 0.4921, Time: 4.75s Epoch: 9, Batch: 530/757, Loss: 0.6236, Time: 4.74s Epoch: 9, Batch: 540/757, Loss: 0.6591, Time: 4.75s Epoch: 9, Batch: 550/757, Loss: 0.8462, Time: 4.74s Epoch: 9, Batch: 560/757, Loss: 0.5659, Time: 4.75s Epoch: 9, Batch: 570/757, Loss: 0.5174, Time: 4.74s Epoch: 9, Batch: 580/757, Loss: 0.3815, Time: 4.74s Epoch: 9, Batch: 590/757, Loss: 0.7845, Time: 4.74s Epoch: 9, Batch: 600/757, Loss: 0.3550, Time: 4.74s Epoch: 9, Batch: 610/757, Loss: 0.8640, Time: 4.73s Epoch: 9, Batch: 620/757, Loss: 0.6665, Time: 4.74s Epoch: 9, Batch: 630/757, Loss: 0.2825, Time: 4.74s Epoch: 9, Batch: 640/757, Loss: 0.6247, Time: 4.73s Epoch: 9, Batch: 650/757, Loss: 0.2500, Time: 4.74s Epoch: 9, Batch: 660/757, Loss: 0.9750, Time: 4.74s Epoch: 9, Batch: 670/757, Loss: 0.7879, Time: 4.73s Epoch: 9, Batch: 680/757, Loss: 0.7807, Time: 4.74s Epoch: 9, Batch: 690/757, Loss: 0.5543, Time: 4.74s Epoch: 9, Batch: 700/757, Loss: 0.4894, Time: 4.74s Epoch: 9, Batch: 710/757, Loss: 0.7026, Time: 4.73s Epoch: 9, Batch: 720/757, Loss: 0.5908, Time: 4.74s Epoch: 9, Batch: 730/757, Loss: 0.3084, Time: 4.74s Epoch: 9, Batch: 740/757, Loss: 0.7142, Time: 4.74s Epoch: 9, Batch: 750/757, Loss: 0.5736, Time: 4.74s Epoch 10/20: Train Loss: 0.5484, Val Loss: 0.5434, Val IoU: 0.3292, Val Dice: 0.3684 Epoch: 10, Batch: 0/757, Loss: 0.6756, Time: 0.87s Epoch: 10, Batch: 10/757, Loss: 0.4733, Time: 4.74s Epoch: 10, Batch: 20/757, Loss: 0.6236, Time: 4.73s Epoch: 10, Batch: 30/757, Loss: 0.5530, Time: 4.74s Epoch: 10, Batch: 40/757, Loss: 0.4705, Time: 4.74s Epoch: 10, Batch: 50/757, Loss: 0.2849, Time: 4.74s Epoch: 10, Batch: 60/757, Loss: 0.5448, Time: 4.73s Epoch: 10, Batch: 70/757, Loss: 0.8213, Time: 4.73s Epoch: 10, Batch: 80/757, Loss: 0.9308, Time: 4.74s Epoch: 10, Batch: 90/757, Loss: 0.6809, Time: 4.73s Epoch: 10, Batch: 100/757, Loss: 0.2859, Time: 4.74s Epoch: 10, Batch: 110/757, Loss: 0.3717, Time: 4.73s Epoch: 10, Batch: 120/757, Loss: 0.3510, Time: 4.73s Epoch: 10, Batch: 130/757, Loss: 0.4744, Time: 4.73s Epoch: 10, Batch: 140/757, Loss: 0.3898, Time: 4.73s Epoch: 10, Batch: 150/757, Loss: 0.3487, Time: 4.73s Epoch: 10, Batch: 160/757, Loss: 0.8526, Time: 4.72s Epoch: 10, Batch: 170/757, Loss: 0.4827, Time: 4.73s Epoch: 10, Batch: 180/757, Loss: 1.2393, Time: 4.73s Epoch: 10, Batch: 190/757, Loss: 0.7805, Time: 4.72s Epoch: 10, Batch: 200/757, Loss: 0.4681, Time: 4.72s Epoch: 10, Batch: 210/757, Loss: 0.6922, Time: 4.73s Epoch: 10, Batch: 220/757, Loss: 0.8136, Time: 4.72s Epoch: 10, Batch: 230/757, Loss: 0.5770, Time: 4.72s Epoch: 10, Batch: 240/757, Loss: 0.5362, Time: 4.73s Epoch: 10, Batch: 250/757, Loss: 0.4322, Time: 4.72s Epoch: 10, Batch: 260/757, Loss: 0.2991, Time: 4.72s Epoch: 10, Batch: 270/757, Loss: 1.1030, Time: 4.72s Epoch: 10, Batch: 280/757, Loss: 0.4833, Time: 4.73s Epoch: 10, Batch: 290/757, Loss: 0.5676, Time: 4.73s Epoch: 10, Batch: 300/757, Loss: 0.7023, Time: 4.73s Epoch: 10, Batch: 310/757, Loss: 0.6714, Time: 4.73s Epoch: 10, Batch: 320/757, Loss: 0.5184, Time: 4.73s Epoch: 10, Batch: 330/757, Loss: 0.6155, Time: 4.73s Epoch: 10, Batch: 340/757, Loss: 0.4704, Time: 4.73s Epoch: 10, Batch: 350/757, Loss: 0.6774, Time: 4.73s Epoch: 10, Batch: 360/757, Loss: 0.6624, Time: 4.74s Epoch: 10, Batch: 370/757, Loss: 0.6815, Time: 4.74s Epoch: 10, Batch: 380/757, Loss: 0.5146, Time: 4.74s Epoch: 10, Batch: 390/757, Loss: 0.6021, Time: 4.74s Epoch: 10, Batch: 400/757, Loss: 0.6141, Time: 4.74s Epoch: 10, Batch: 410/757, Loss: 0.4082, Time: 4.74s Epoch: 10, Batch: 420/757, Loss: 0.4954, Time: 4.74s Epoch: 10, Batch: 430/757, Loss: 0.3436, Time: 4.73s Epoch: 10, Batch: 440/757, Loss: 0.7393, Time: 4.74s Epoch: 10, Batch: 450/757, Loss: 1.0566, Time: 4.74s Epoch: 10, Batch: 460/757, Loss: 0.7543, Time: 4.74s Epoch: 10, Batch: 470/757, Loss: 0.7157, Time: 4.73s Epoch: 10, Batch: 480/757, Loss: 0.3405, Time: 4.73s Epoch: 10, Batch: 490/757, Loss: 0.5710, Time: 4.73s Epoch: 10, Batch: 500/757, Loss: 0.6620, Time: 4.73s Epoch: 10, Batch: 510/757, Loss: 0.6066, Time: 4.73s Epoch: 10, Batch: 520/757, Loss: 0.4905, Time: 4.73s Epoch: 10, Batch: 530/757, Loss: 0.6552, Time: 4.73s Epoch: 10, Batch: 540/757, Loss: 0.5169, Time: 4.73s Epoch: 10, Batch: 550/757, Loss: 0.5163, Time: 4.73s Epoch: 10, Batch: 560/757, Loss: 0.6095, Time: 4.73s Epoch: 10, Batch: 570/757, Loss: 0.4086, Time: 4.72s Epoch: 10, Batch: 580/757, Loss: 0.5715, Time: 4.72s Epoch: 10, Batch: 590/757, Loss: 0.5511, Time: 4.73s Epoch: 10, Batch: 600/757, Loss: 0.6913, Time: 4.73s Epoch: 10, Batch: 610/757, Loss: 0.7067, Time: 4.73s Epoch: 10, Batch: 620/757, Loss: 0.6059, Time: 4.72s Epoch: 10, Batch: 630/757, Loss: 0.3114, Time: 4.72s Epoch: 10, Batch: 640/757, Loss: 0.5573, Time: 4.72s Epoch: 10, Batch: 650/757, Loss: 0.4735, Time: 4.73s Epoch: 10, Batch: 660/757, Loss: 0.6376, Time: 4.73s Epoch: 10, Batch: 670/757, Loss: 0.4724, Time: 4.73s Epoch: 10, Batch: 680/757, Loss: 0.3533, Time: 4.73s Epoch: 10, Batch: 690/757, Loss: 0.5117, Time: 4.72s Epoch: 10, Batch: 700/757, Loss: 0.3668, Time: 4.73s Epoch: 10, Batch: 710/757, Loss: 0.4990, Time: 4.73s Epoch: 10, Batch: 720/757, Loss: 0.5665, Time: 4.73s Epoch: 10, Batch: 730/757, Loss: 0.3421, Time: 4.73s Epoch: 10, Batch: 740/757, Loss: 0.5515, Time: 4.72s Epoch: 10, Batch: 750/757, Loss: 0.5026, Time: 4.73s Epoch 11/20: Train Loss: 0.5466, Val Loss: 0.5530, Val IoU: 0.3146, Val Dice: 0.3547 Epoch: 11, Batch: 0/757, Loss: 0.5463, Time: 0.85s Epoch: 11, Batch: 10/757, Loss: 0.2064, Time: 4.73s Epoch: 11, Batch: 20/757, Loss: 0.7656, Time: 4.73s Epoch: 11, Batch: 30/757, Loss: 0.6483, Time: 4.73s Epoch: 11, Batch: 40/757, Loss: 0.4202, Time: 4.73s Epoch: 11, Batch: 50/757, Loss: 0.5992, Time: 4.73s Epoch: 11, Batch: 60/757, Loss: 0.3061, Time: 4.73s Epoch: 11, Batch: 70/757, Loss: 0.7999, Time: 4.73s Epoch: 11, Batch: 80/757, Loss: 0.6193, Time: 4.74s Epoch: 11, Batch: 90/757, Loss: 0.4750, Time: 4.74s Epoch: 11, Batch: 100/757, Loss: 0.6364, Time: 4.73s Epoch: 11, Batch: 110/757, Loss: 0.3119, Time: 4.73s Epoch: 11, Batch: 120/757, Loss: 0.2563, Time: 4.73s Epoch: 11, Batch: 130/757, Loss: 0.5267, Time: 4.73s Epoch: 11, Batch: 140/757, Loss: 0.5181, Time: 4.72s Epoch: 11, Batch: 150/757, Loss: 0.6639, Time: 4.73s Epoch: 11, Batch: 160/757, Loss: 0.5773, Time: 4.72s Epoch: 11, Batch: 170/757, Loss: 0.3519, Time: 4.72s Epoch: 11, Batch: 180/757, Loss: 0.7060, Time: 4.72s Epoch: 11, Batch: 190/757, Loss: 0.8662, Time: 4.72s Epoch: 11, Batch: 200/757, Loss: 0.4242, Time: 4.72s Epoch: 11, Batch: 210/757, Loss: 0.6512, Time: 4.72s Epoch: 11, Batch: 220/757, Loss: 0.7330, Time: 4.72s Epoch: 11, Batch: 230/757, Loss: 0.5546, Time: 4.73s Epoch: 11, Batch: 240/757, Loss: 0.4962, Time: 4.73s Epoch: 11, Batch: 250/757, Loss: 0.4806, Time: 4.73s Epoch: 11, Batch: 260/757, Loss: 0.7626, Time: 4.72s Epoch: 11, Batch: 270/757, Loss: 0.5030, Time: 4.73s Epoch: 11, Batch: 280/757, Loss: 0.8481, Time: 4.73s Epoch: 11, Batch: 290/757, Loss: 0.5521, Time: 4.73s Epoch: 11, Batch: 300/757, Loss: 0.5095, Time: 4.73s Epoch: 11, Batch: 310/757, Loss: 0.4663, Time: 4.73s Epoch: 11, Batch: 320/757, Loss: 0.9861, Time: 4.73s Epoch: 11, Batch: 330/757, Loss: 0.3980, Time: 4.74s Epoch: 11, Batch: 340/757, Loss: 0.5050, Time: 4.73s Epoch: 11, Batch: 350/757, Loss: 0.2477, Time: 4.74s Epoch: 11, Batch: 360/757, Loss: 0.6794, Time: 4.74s Epoch: 11, Batch: 370/757, Loss: 0.7125, Time: 4.74s Epoch: 11, Batch: 380/757, Loss: 1.1754, Time: 4.74s Epoch: 11, Batch: 390/757, Loss: 0.6146, Time: 4.74s Epoch: 11, Batch: 400/757, Loss: 0.4079, Time: 4.74s Epoch: 11, Batch: 410/757, Loss: 0.6135, Time: 4.74s Epoch: 11, Batch: 420/757, Loss: 0.4809, Time: 4.74s Epoch: 11, Batch: 430/757, Loss: 1.0944, Time: 4.74s Epoch: 11, Batch: 440/757, Loss: 0.8810, Time: 4.74s Epoch: 11, Batch: 450/757, Loss: 0.4464, Time: 4.74s Epoch: 11, Batch: 460/757, Loss: 0.4880, Time: 4.74s Epoch: 11, Batch: 470/757, Loss: 0.6428, Time: 4.74s Epoch: 11, Batch: 480/757, Loss: 1.0033, Time: 4.73s Epoch: 11, Batch: 490/757, Loss: 0.4687, Time: 4.73s Epoch: 11, Batch: 500/757, Loss: 0.6524, Time: 4.74s Epoch: 11, Batch: 510/757, Loss: 0.5403, Time: 4.74s Epoch: 11, Batch: 520/757, Loss: 0.4680, Time: 4.74s Epoch: 11, Batch: 530/757, Loss: 0.7459, Time: 4.73s Epoch: 11, Batch: 540/757, Loss: 0.3653, Time: 4.74s Epoch: 11, Batch: 550/757, Loss: 0.2888, Time: 4.74s Epoch: 11, Batch: 560/757, Loss: 0.4404, Time: 4.74s Epoch: 11, Batch: 570/757, Loss: 0.6740, Time: 4.73s Epoch: 11, Batch: 580/757, Loss: 0.4040, Time: 4.73s Epoch: 11, Batch: 590/757, Loss: 0.3068, Time: 4.73s Epoch: 11, Batch: 600/757, Loss: 0.5687, Time: 4.73s Epoch: 11, Batch: 610/757, Loss: 0.2646, Time: 4.73s Epoch: 11, Batch: 620/757, Loss: 0.9064, Time: 4.73s Epoch: 11, Batch: 630/757, Loss: 0.2676, Time: 4.74s Epoch: 11, Batch: 640/757, Loss: 0.2803, Time: 4.73s Epoch: 11, Batch: 650/757, Loss: 0.4380, Time: 4.73s Epoch: 11, Batch: 660/757, Loss: 0.5429, Time: 4.73s Epoch: 11, Batch: 670/757, Loss: 0.3283, Time: 4.74s Epoch: 11, Batch: 680/757, Loss: 0.4375, Time: 4.73s Epoch: 11, Batch: 690/757, Loss: 0.2874, Time: 4.73s Epoch: 11, Batch: 700/757, Loss: 0.2605, Time: 4.74s Epoch: 11, Batch: 710/757, Loss: 1.0611, Time: 4.74s Epoch: 11, Batch: 720/757, Loss: 0.2269, Time: 4.74s Epoch: 11, Batch: 730/757, Loss: 0.3829, Time: 4.74s Epoch: 11, Batch: 740/757, Loss: 0.4017, Time: 4.74s Epoch: 11, Batch: 750/757, Loss: 0.7437, Time: 4.74s Epoch 12/20: Train Loss: 0.5462, Val Loss: 0.5196, Val IoU: 0.3409, Val Dice: 0.3806 Saving best model with IoU: 0.3409 Epoch: 12, Batch: 0/757, Loss: 0.6074, Time: 0.86s Epoch: 12, Batch: 10/757, Loss: 0.4775, Time: 4.73s Epoch: 12, Batch: 20/757, Loss: 0.4261, Time: 4.74s Epoch: 12, Batch: 30/757, Loss: 0.5057, Time: 4.73s Epoch: 12, Batch: 40/757, Loss: 0.3105, Time: 4.74s Epoch: 12, Batch: 50/757, Loss: 0.4812, Time: 4.74s Epoch: 12, Batch: 60/757, Loss: 0.9578, Time: 4.74s Epoch: 12, Batch: 70/757, Loss: 0.3197, Time: 4.75s Epoch: 12, Batch: 80/757, Loss: 0.5241, Time: 4.74s Epoch: 12, Batch: 90/757, Loss: 0.5286, Time: 4.74s Epoch: 12, Batch: 100/757, Loss: 0.5181, Time: 4.74s Epoch: 12, Batch: 110/757, Loss: 0.7207, Time: 4.74s Epoch: 12, Batch: 120/757, Loss: 0.6019, Time: 4.74s Epoch: 12, Batch: 130/757, Loss: 0.8644, Time: 4.74s Epoch: 12, Batch: 140/757, Loss: 0.4413, Time: 4.74s Epoch: 12, Batch: 150/757, Loss: 0.8707, Time: 4.74s Epoch: 12, Batch: 160/757, Loss: 0.3796, Time: 4.74s Epoch: 12, Batch: 170/757, Loss: 0.4599, Time: 4.74s Epoch: 12, Batch: 180/757, Loss: 0.3151, Time: 4.74s Epoch: 12, Batch: 190/757, Loss: 0.5616, Time: 4.75s Epoch: 12, Batch: 200/757, Loss: 0.9008, Time: 4.75s Epoch: 12, Batch: 210/757, Loss: 0.7471, Time: 4.74s Epoch: 12, Batch: 220/757, Loss: 0.3682, Time: 4.74s Epoch: 12, Batch: 230/757, Loss: 0.5774, Time: 4.74s Epoch: 12, Batch: 240/757, Loss: 0.5619, Time: 4.74s Epoch: 12, Batch: 250/757, Loss: 0.4510, Time: 4.75s Epoch: 12, Batch: 260/757, Loss: 0.4099, Time: 4.74s Epoch: 12, Batch: 270/757, Loss: 0.4700, Time: 4.74s Epoch: 12, Batch: 280/757, Loss: 0.9393, Time: 4.74s Epoch: 12, Batch: 290/757, Loss: 0.6809, Time: 4.73s Epoch: 12, Batch: 300/757, Loss: 0.3268, Time: 4.74s Epoch: 12, Batch: 310/757, Loss: 0.4924, Time: 4.74s Epoch: 12, Batch: 320/757, Loss: 0.3062, Time: 4.74s Epoch: 12, Batch: 330/757, Loss: 0.4893, Time: 4.74s Epoch: 12, Batch: 340/757, Loss: 0.3732, Time: 4.74s Epoch: 12, Batch: 350/757, Loss: 0.3283, Time: 4.74s Epoch: 12, Batch: 360/757, Loss: 0.5563, Time: 4.74s Epoch: 12, Batch: 370/757, Loss: 0.3068, Time: 4.74s Epoch: 12, Batch: 380/757, Loss: 0.2006, Time: 4.74s Epoch: 12, Batch: 390/757, Loss: 0.8539, Time: 4.74s Epoch: 12, Batch: 400/757, Loss: 0.5987, Time: 4.74s Epoch: 12, Batch: 410/757, Loss: 0.3036, Time: 4.74s Epoch: 12, Batch: 420/757, Loss: 0.4875, Time: 4.74s Epoch: 12, Batch: 430/757, Loss: 1.0150, Time: 4.74s Epoch: 12, Batch: 440/757, Loss: 0.5418, Time: 4.74s Epoch: 12, Batch: 450/757, Loss: 0.7427, Time: 4.74s Epoch: 12, Batch: 460/757, Loss: 0.5030, Time: 4.74s Epoch: 12, Batch: 470/757, Loss: 0.3227, Time: 4.75s Epoch: 12, Batch: 480/757, Loss: 0.9568, Time: 4.75s Epoch: 12, Batch: 490/757, Loss: 0.9896, Time: 4.75s Epoch: 12, Batch: 500/757, Loss: 0.4956, Time: 4.74s Epoch: 12, Batch: 510/757, Loss: 0.5663, Time: 4.74s Epoch: 12, Batch: 520/757, Loss: 0.2543, Time: 4.75s Epoch: 12, Batch: 530/757, Loss: 0.5511, Time: 4.75s Epoch: 12, Batch: 540/757, Loss: 0.3340, Time: 4.74s Epoch: 12, Batch: 550/757, Loss: 0.5767, Time: 4.75s Epoch: 12, Batch: 560/757, Loss: 0.3265, Time: 4.74s Epoch: 12, Batch: 570/757, Loss: 0.4089, Time: 4.74s Epoch: 12, Batch: 580/757, Loss: 0.4180, Time: 4.75s Epoch: 12, Batch: 590/757, Loss: 0.8032, Time: 4.74s Epoch: 12, Batch: 600/757, Loss: 0.3931, Time: 4.74s Epoch: 12, Batch: 610/757, Loss: 0.4157, Time: 4.74s Epoch: 12, Batch: 620/757, Loss: 0.4702, Time: 4.74s Epoch: 12, Batch: 630/757, Loss: 0.5102, Time: 4.75s Epoch: 12, Batch: 640/757, Loss: 0.3355, Time: 4.74s Epoch: 12, Batch: 650/757, Loss: 0.5555, Time: 4.75s Epoch: 12, Batch: 660/757, Loss: 0.5535, Time: 4.74s Epoch: 12, Batch: 670/757, Loss: 0.5149, Time: 4.74s Epoch: 12, Batch: 680/757, Loss: 0.5200, Time: 4.75s Epoch: 12, Batch: 690/757, Loss: 0.8139, Time: 4.75s Epoch: 12, Batch: 700/757, Loss: 0.5110, Time: 4.75s Epoch: 12, Batch: 710/757, Loss: 0.5682, Time: 4.75s Epoch: 12, Batch: 720/757, Loss: 0.4767, Time: 4.75s Epoch: 12, Batch: 730/757, Loss: 0.2897, Time: 4.75s Epoch: 12, Batch: 740/757, Loss: 0.6810, Time: 4.75s Epoch: 12, Batch: 750/757, Loss: 0.2477, Time: 4.75s Epoch 13/20: Train Loss: 0.5344, Val Loss: 0.5548, Val IoU: 0.3234, Val Dice: 0.3638 Epoch: 13, Batch: 0/757, Loss: 0.3312, Time: 0.83s Epoch: 13, Batch: 10/757, Loss: 0.3518, Time: 4.74s Epoch: 13, Batch: 20/757, Loss: 0.5675, Time: 4.74s Epoch: 13, Batch: 30/757, Loss: 0.4674, Time: 4.74s Epoch: 13, Batch: 40/757, Loss: 0.5691, Time: 4.73s Epoch: 13, Batch: 50/757, Loss: 0.4730, Time: 4.73s Epoch: 13, Batch: 60/757, Loss: 0.5181, Time: 4.73s Epoch: 13, Batch: 70/757, Loss: 0.9085, Time: 4.74s Epoch: 13, Batch: 80/757, Loss: 0.3244, Time: 4.74s Epoch: 13, Batch: 90/757, Loss: 1.0515, Time: 4.74s Epoch: 13, Batch: 100/757, Loss: 0.5731, Time: 4.74s Epoch: 13, Batch: 110/757, Loss: 0.2698, Time: 4.73s Epoch: 13, Batch: 120/757, Loss: 0.4800, Time: 4.73s Epoch: 13, Batch: 130/757, Loss: 1.1101, Time: 4.73s Epoch: 13, Batch: 140/757, Loss: 0.3583, Time: 4.73s Epoch: 13, Batch: 150/757, Loss: 0.9263, Time: 4.73s Epoch: 13, Batch: 160/757, Loss: 0.2718, Time: 4.73s Epoch: 13, Batch: 170/757, Loss: 0.4479, Time: 4.74s Epoch: 13, Batch: 180/757, Loss: 0.4093, Time: 4.73s Epoch: 13, Batch: 190/757, Loss: 0.4853, Time: 4.73s Epoch: 13, Batch: 200/757, Loss: 0.4726, Time: 4.74s Epoch: 13, Batch: 210/757, Loss: 0.5380, Time: 4.73s Epoch: 13, Batch: 220/757, Loss: 0.7040, Time: 4.74s Epoch: 13, Batch: 230/757, Loss: 0.6230, Time: 4.73s Epoch: 13, Batch: 240/757, Loss: 0.2969, Time: 4.74s Epoch: 13, Batch: 250/757, Loss: 0.7507, Time: 4.74s Epoch: 13, Batch: 260/757, Loss: 1.2451, Time: 4.74s Epoch: 13, Batch: 270/757, Loss: 0.2513, Time: 4.74s Epoch: 13, Batch: 280/757, Loss: 0.6283, Time: 4.73s Epoch: 13, Batch: 290/757, Loss: 0.2711, Time: 4.74s Epoch: 13, Batch: 300/757, Loss: 0.3314, Time: 4.74s Epoch: 13, Batch: 310/757, Loss: 0.3001, Time: 4.73s Epoch: 13, Batch: 320/757, Loss: 0.3091, Time: 4.74s Epoch: 13, Batch: 330/757, Loss: 0.2348, Time: 4.74s Epoch: 13, Batch: 340/757, Loss: 0.5272, Time: 4.74s Epoch: 13, Batch: 350/757, Loss: 0.6281, Time: 4.74s Epoch: 13, Batch: 360/757, Loss: 1.2637, Time: 4.75s Epoch: 13, Batch: 370/757, Loss: 0.5856, Time: 4.74s Epoch: 13, Batch: 380/757, Loss: 0.5249, Time: 4.74s Epoch: 13, Batch: 390/757, Loss: 0.6309, Time: 4.74s Epoch: 13, Batch: 400/757, Loss: 0.8167, Time: 4.74s Epoch: 13, Batch: 410/757, Loss: 0.4053, Time: 4.75s Epoch: 13, Batch: 420/757, Loss: 0.3836, Time: 4.74s Epoch: 13, Batch: 430/757, Loss: 0.3942, Time: 4.74s Epoch: 13, Batch: 440/757, Loss: 0.9115, Time: 4.74s Epoch: 13, Batch: 450/757, Loss: 0.6008, Time: 4.74s Epoch: 13, Batch: 460/757, Loss: 0.6198, Time: 4.75s Epoch: 13, Batch: 470/757, Loss: 0.5223, Time: 4.75s Epoch: 13, Batch: 480/757, Loss: 0.7156, Time: 4.74s Epoch: 13, Batch: 490/757, Loss: 0.4157, Time: 4.75s Epoch: 13, Batch: 500/757, Loss: 0.4937, Time: 4.75s Epoch: 13, Batch: 510/757, Loss: 0.5553, Time: 4.74s Epoch: 13, Batch: 520/757, Loss: 0.3708, Time: 4.73s Epoch: 13, Batch: 530/757, Loss: 0.6236, Time: 4.74s Epoch: 13, Batch: 540/757, Loss: 0.6960, Time: 4.74s Epoch: 13, Batch: 550/757, Loss: 0.6697, Time: 4.74s Epoch: 13, Batch: 560/757, Loss: 0.5854, Time: 4.74s Epoch: 13, Batch: 570/757, Loss: 0.3066, Time: 4.74s Epoch: 13, Batch: 580/757, Loss: 0.8670, Time: 4.73s Epoch: 13, Batch: 590/757, Loss: 0.7833, Time: 4.73s Epoch: 13, Batch: 600/757, Loss: 0.3810, Time: 4.73s Epoch: 13, Batch: 610/757, Loss: 0.3759, Time: 4.73s Epoch: 13, Batch: 620/757, Loss: 0.6532, Time: 4.73s Epoch: 13, Batch: 630/757, Loss: 0.3772, Time: 4.73s Epoch: 13, Batch: 640/757, Loss: 0.4803, Time: 4.73s Epoch: 13, Batch: 650/757, Loss: 0.4744, Time: 4.73s Epoch: 13, Batch: 660/757, Loss: 0.4951, Time: 4.73s Epoch: 13, Batch: 670/757, Loss: 0.4715, Time: 4.73s Epoch: 13, Batch: 680/757, Loss: 1.0591, Time: 4.74s Epoch: 13, Batch: 690/757, Loss: 0.7246, Time: 4.73s Epoch: 13, Batch: 700/757, Loss: 0.6236, Time: 4.74s Epoch: 13, Batch: 710/757, Loss: 0.5593, Time: 4.73s Epoch: 13, Batch: 720/757, Loss: 0.5035, Time: 4.73s Epoch: 13, Batch: 730/757, Loss: 0.6273, Time: 4.74s Epoch: 13, Batch: 740/757, Loss: 0.7505, Time: 4.73s Epoch: 13, Batch: 750/757, Loss: 0.3566, Time: 4.73s Epoch 14/20: Train Loss: 0.5308, Val Loss: 0.5783, Val IoU: 0.3292, Val Dice: 0.3684 Epoch: 14, Batch: 0/757, Loss: 1.0243, Time: 0.88s Epoch: 14, Batch: 10/757, Loss: 0.5290, Time: 4.72s Epoch: 14, Batch: 20/757, Loss: 0.2428, Time: 4.72s Epoch: 14, Batch: 30/757, Loss: 0.7499, Time: 4.72s Epoch: 14, Batch: 40/757, Loss: 0.5854, Time: 4.73s Epoch: 14, Batch: 50/757, Loss: 0.3372, Time: 4.73s Epoch: 14, Batch: 60/757, Loss: 0.4051, Time: 4.73s Epoch: 14, Batch: 70/757, Loss: 0.6086, Time: 4.73s Epoch: 14, Batch: 80/757, Loss: 0.6513, Time: 4.73s Epoch: 14, Batch: 90/757, Loss: 0.6382, Time: 4.73s Epoch: 14, Batch: 100/757, Loss: 0.2985, Time: 4.73s Epoch: 14, Batch: 110/757, Loss: 0.2443, Time: 4.73s Epoch: 14, Batch: 120/757, Loss: 0.3137, Time: 4.73s Epoch: 14, Batch: 130/757, Loss: 0.4819, Time: 4.72s Epoch: 14, Batch: 140/757, Loss: 0.5066, Time: 4.73s Epoch: 14, Batch: 150/757, Loss: 0.5140, Time: 4.73s Epoch: 14, Batch: 160/757, Loss: 0.4360, Time: 4.73s Epoch: 14, Batch: 170/757, Loss: 0.5361, Time: 4.73s Epoch: 14, Batch: 180/757, Loss: 0.7466, Time: 4.73s Epoch: 14, Batch: 190/757, Loss: 0.6351, Time: 4.74s Epoch: 14, Batch: 200/757, Loss: 0.4989, Time: 4.74s Epoch: 14, Batch: 210/757, Loss: 0.5948, Time: 4.73s Epoch: 14, Batch: 220/757, Loss: 0.6898, Time: 4.74s Epoch: 14, Batch: 230/757, Loss: 0.4433, Time: 4.74s Epoch: 14, Batch: 240/757, Loss: 0.8367, Time: 4.73s Epoch: 14, Batch: 250/757, Loss: 0.6278, Time: 4.74s Epoch: 14, Batch: 260/757, Loss: 0.4103, Time: 4.73s Epoch: 14, Batch: 270/757, Loss: 0.5048, Time: 4.74s Epoch: 14, Batch: 280/757, Loss: 0.2388, Time: 4.74s Epoch: 14, Batch: 290/757, Loss: 1.0119, Time: 4.74s Epoch: 14, Batch: 300/757, Loss: 0.5996, Time: 4.74s Epoch: 14, Batch: 310/757, Loss: 1.1100, Time: 4.74s Epoch: 14, Batch: 320/757, Loss: 0.4973, Time: 4.75s Epoch: 14, Batch: 330/757, Loss: 0.6002, Time: 4.74s Epoch: 14, Batch: 340/757, Loss: 0.3106, Time: 4.74s Epoch: 14, Batch: 350/757, Loss: 0.7164, Time: 4.74s Epoch: 14, Batch: 360/757, Loss: 1.3494, Time: 4.75s Epoch: 14, Batch: 370/757, Loss: 0.8771, Time: 4.74s Epoch: 14, Batch: 380/757, Loss: 0.4697, Time: 4.74s Epoch: 14, Batch: 390/757, Loss: 0.7441, Time: 4.74s Epoch: 14, Batch: 400/757, Loss: 0.3971, Time: 4.74s Epoch: 14, Batch: 410/757, Loss: 0.5052, Time: 4.75s Epoch: 14, Batch: 420/757, Loss: 0.7339, Time: 4.75s Epoch: 14, Batch: 430/757, Loss: 0.5677, Time: 4.74s Epoch: 14, Batch: 440/757, Loss: 0.5526, Time: 4.75s Epoch: 14, Batch: 450/757, Loss: 0.4075, Time: 4.75s Epoch: 14, Batch: 460/757, Loss: 0.5893, Time: 4.75s Epoch: 14, Batch: 470/757, Loss: 0.2327, Time: 4.75s Epoch: 14, Batch: 480/757, Loss: 0.2717, Time: 4.75s Epoch: 14, Batch: 490/757, Loss: 0.4951, Time: 4.74s Epoch: 14, Batch: 500/757, Loss: 0.4827, Time: 4.75s Epoch: 14, Batch: 510/757, Loss: 0.3855, Time: 4.75s Epoch: 14, Batch: 520/757, Loss: 0.3088, Time: 4.75s Epoch: 14, Batch: 530/757, Loss: 0.7909, Time: 4.76s Epoch: 14, Batch: 540/757, Loss: 0.3818, Time: 4.75s Epoch: 14, Batch: 550/757, Loss: 0.5561, Time: 4.75s Epoch: 14, Batch: 560/757, Loss: 0.6892, Time: 4.75s Epoch: 14, Batch: 570/757, Loss: 0.4192, Time: 4.75s Epoch: 14, Batch: 580/757, Loss: 0.3811, Time: 4.75s Epoch: 14, Batch: 590/757, Loss: 0.6916, Time: 4.75s Epoch: 14, Batch: 600/757, Loss: 0.9035, Time: 4.75s Epoch: 14, Batch: 610/757, Loss: 0.2914, Time: 4.76s Epoch: 14, Batch: 620/757, Loss: 0.3904, Time: 4.75s Epoch: 14, Batch: 630/757, Loss: 0.4942, Time: 4.75s Epoch: 14, Batch: 640/757, Loss: 0.4470, Time: 4.74s Epoch: 14, Batch: 650/757, Loss: 0.4350, Time: 4.75s Epoch: 14, Batch: 660/757, Loss: 0.2370, Time: 4.74s Epoch: 14, Batch: 670/757, Loss: 0.2870, Time: 4.74s Epoch: 14, Batch: 680/757, Loss: 0.4608, Time: 4.74s Epoch: 14, Batch: 690/757, Loss: 0.4214, Time: 4.75s Epoch: 14, Batch: 700/757, Loss: 0.5658, Time: 4.75s Epoch: 14, Batch: 710/757, Loss: 0.4304, Time: 4.75s Epoch: 14, Batch: 720/757, Loss: 0.5379, Time: 4.74s Epoch: 14, Batch: 730/757, Loss: 0.5274, Time: 4.74s Epoch: 14, Batch: 740/757, Loss: 0.5734, Time: 4.75s Epoch: 14, Batch: 750/757, Loss: 0.6961, Time: 4.75s Epoch 15/20: Train Loss: 0.5225, Val Loss: 0.5148, Val IoU: 0.3351, Val Dice: 0.3745 Epoch: 15, Batch: 0/757, Loss: 0.4426, Time: 0.82s Epoch: 15, Batch: 10/757, Loss: 0.4591, Time: 4.73s Epoch: 15, Batch: 20/757, Loss: 0.7569, Time: 4.73s Epoch: 15, Batch: 30/757, Loss: 0.3982, Time: 4.74s Epoch: 15, Batch: 40/757, Loss: 0.9817, Time: 4.73s Epoch: 15, Batch: 50/757, Loss: 0.3612, Time: 4.73s Epoch: 15, Batch: 60/757, Loss: 0.5820, Time: 4.73s Epoch: 15, Batch: 70/757, Loss: 0.5443, Time: 4.73s Epoch: 15, Batch: 80/757, Loss: 0.2916, Time: 4.73s Epoch: 15, Batch: 90/757, Loss: 0.2754, Time: 4.73s Epoch: 15, Batch: 100/757, Loss: 0.2841, Time: 4.73s Epoch: 15, Batch: 110/757, Loss: 0.4504, Time: 4.74s Epoch: 15, Batch: 120/757, Loss: 0.5560, Time: 4.73s Epoch: 15, Batch: 130/757, Loss: 0.6363, Time: 4.73s Epoch: 15, Batch: 140/757, Loss: 0.4693, Time: 4.74s Epoch: 15, Batch: 150/757, Loss: 0.4755, Time: 4.74s Epoch: 15, Batch: 160/757, Loss: 0.3279, Time: 4.73s Epoch: 15, Batch: 170/757, Loss: 0.3851, Time: 4.73s Epoch: 15, Batch: 180/757, Loss: 0.5118, Time: 4.74s Epoch: 15, Batch: 190/757, Loss: 0.4291, Time: 4.74s Epoch: 15, Batch: 200/757, Loss: 0.8899, Time: 4.74s Epoch: 15, Batch: 210/757, Loss: 0.6855, Time: 4.74s Epoch: 15, Batch: 220/757, Loss: 0.6454, Time: 4.74s Epoch: 15, Batch: 230/757, Loss: 0.3111, Time: 4.75s Epoch: 15, Batch: 240/757, Loss: 0.3974, Time: 4.75s Epoch: 15, Batch: 250/757, Loss: 0.3639, Time: 4.75s Epoch: 15, Batch: 260/757, Loss: 0.5263, Time: 4.75s Epoch: 15, Batch: 270/757, Loss: 0.3690, Time: 4.75s Epoch: 15, Batch: 280/757, Loss: 0.4421, Time: 4.76s Epoch: 15, Batch: 290/757, Loss: 0.5102, Time: 4.75s Epoch: 15, Batch: 300/757, Loss: 0.7447, Time: 4.75s Epoch: 15, Batch: 310/757, Loss: 0.5337, Time: 4.75s Epoch: 15, Batch: 320/757, Loss: 0.6762, Time: 4.75s Epoch: 15, Batch: 330/757, Loss: 0.6490, Time: 4.75s Epoch: 15, Batch: 340/757, Loss: 0.4278, Time: 4.75s Epoch: 15, Batch: 350/757, Loss: 0.7589, Time: 4.75s Epoch: 15, Batch: 360/757, Loss: 0.6920, Time: 4.75s Epoch: 15, Batch: 370/757, Loss: 0.5425, Time: 4.74s Epoch: 15, Batch: 380/757, Loss: 0.4721, Time: 4.75s Epoch: 15, Batch: 390/757, Loss: 0.3366, Time: 4.74s Epoch: 15, Batch: 400/757, Loss: 0.6290, Time: 4.76s Epoch: 15, Batch: 410/757, Loss: 0.3800, Time: 4.75s Epoch: 15, Batch: 420/757, Loss: 0.7153, Time: 4.75s Epoch: 15, Batch: 430/757, Loss: 0.4438, Time: 4.75s Epoch: 15, Batch: 440/757, Loss: 0.4862, Time: 4.75s Epoch: 15, Batch: 450/757, Loss: 0.4298, Time: 4.76s Epoch: 15, Batch: 460/757, Loss: 0.6545, Time: 4.75s Epoch: 15, Batch: 470/757, Loss: 0.6694, Time: 4.76s Epoch: 15, Batch: 480/757, Loss: 0.5922, Time: 4.75s Epoch: 15, Batch: 490/757, Loss: 0.7740, Time: 4.76s Epoch: 15, Batch: 500/757, Loss: 0.2832, Time: 4.75s Epoch: 15, Batch: 510/757, Loss: 0.5081, Time: 4.75s Epoch: 15, Batch: 520/757, Loss: 0.3058, Time: 4.75s Epoch: 15, Batch: 530/757, Loss: 0.3687, Time: 4.75s Epoch: 15, Batch: 540/757, Loss: 0.7631, Time: 4.75s Epoch: 15, Batch: 550/757, Loss: 0.4568, Time: 4.75s Epoch: 15, Batch: 560/757, Loss: 0.5073, Time: 4.75s Epoch: 15, Batch: 570/757, Loss: 0.2106, Time: 4.76s Epoch: 15, Batch: 580/757, Loss: 0.7476, Time: 4.76s Epoch: 15, Batch: 590/757, Loss: 0.3841, Time: 4.75s Epoch: 15, Batch: 600/757, Loss: 0.5782, Time: 4.75s Epoch: 15, Batch: 610/757, Loss: 0.6566, Time: 4.75s Epoch: 15, Batch: 620/757, Loss: 0.5964, Time: 4.75s Epoch: 15, Batch: 630/757, Loss: 1.0600, Time: 4.75s Epoch: 15, Batch: 640/757, Loss: 0.4587, Time: 4.75s Epoch: 15, Batch: 650/757, Loss: 0.2971, Time: 4.75s Epoch: 15, Batch: 660/757, Loss: 0.5749, Time: 4.76s Epoch: 15, Batch: 670/757, Loss: 0.7520, Time: 4.75s Epoch: 15, Batch: 680/757, Loss: 0.3674, Time: 4.75s Epoch: 15, Batch: 690/757, Loss: 0.4576, Time: 4.75s Epoch: 15, Batch: 700/757, Loss: 0.6250, Time: 4.75s Epoch: 15, Batch: 710/757, Loss: 0.5991, Time: 4.74s Epoch: 15, Batch: 720/757, Loss: 0.4182, Time: 4.75s Epoch: 15, Batch: 730/757, Loss: 0.9671, Time: 4.75s Epoch: 15, Batch: 740/757, Loss: 0.5218, Time: 4.75s Epoch: 15, Batch: 750/757, Loss: 0.6652, Time: 4.74s Epoch 16/20: Train Loss: 0.5205, Val Loss: 0.5376, Val IoU: 0.3238, Val Dice: 0.3618 Epoch: 16, Batch: 0/757, Loss: 0.3807, Time: 0.85s Epoch: 16, Batch: 10/757, Loss: 0.3801, Time: 4.74s Epoch: 16, Batch: 20/757, Loss: 0.3794, Time: 4.74s Epoch: 16, Batch: 30/757, Loss: 0.4990, Time: 4.74s Epoch: 16, Batch: 40/757, Loss: 0.4076, Time: 4.74s Epoch: 16, Batch: 50/757, Loss: 0.3050, Time: 4.75s Epoch: 16, Batch: 60/757, Loss: 0.9433, Time: 4.74s Epoch: 16, Batch: 70/757, Loss: 0.6085, Time: 4.73s Epoch: 16, Batch: 80/757, Loss: 0.7458, Time: 4.73s Epoch: 16, Batch: 90/757, Loss: 0.4746, Time: 4.74s Epoch: 16, Batch: 100/757, Loss: 0.5161, Time: 4.74s Epoch: 16, Batch: 110/757, Loss: 0.4196, Time: 4.73s Epoch: 16, Batch: 120/757, Loss: 0.3633, Time: 4.74s Epoch: 16, Batch: 130/757, Loss: 0.4620, Time: 4.74s Epoch: 16, Batch: 140/757, Loss: 0.3837, Time: 4.73s Epoch: 16, Batch: 150/757, Loss: 0.4993, Time: 4.74s Epoch: 16, Batch: 160/757, Loss: 0.4901, Time: 4.73s Epoch: 16, Batch: 170/757, Loss: 0.7737, Time: 4.74s Epoch: 16, Batch: 180/757, Loss: 0.6103, Time: 4.74s Epoch: 16, Batch: 190/757, Loss: 0.7598, Time: 4.74s Epoch: 16, Batch: 200/757, Loss: 0.4301, Time: 4.73s Epoch: 16, Batch: 210/757, Loss: 0.6343, Time: 4.74s Epoch: 16, Batch: 220/757, Loss: 0.2903, Time: 4.74s Epoch: 16, Batch: 230/757, Loss: 0.3244, Time: 4.75s Epoch: 16, Batch: 240/757, Loss: 0.2775, Time: 4.75s Epoch: 16, Batch: 250/757, Loss: 0.3046, Time: 4.74s Epoch: 16, Batch: 260/757, Loss: 0.3182, Time: 4.74s Epoch: 16, Batch: 270/757, Loss: 1.3976, Time: 4.75s Epoch: 16, Batch: 280/757, Loss: 0.6426, Time: 4.75s Epoch: 16, Batch: 290/757, Loss: 0.5741, Time: 4.75s Epoch: 16, Batch: 300/757, Loss: 0.5327, Time: 4.75s Epoch: 16, Batch: 310/757, Loss: 0.4568, Time: 4.75s Epoch: 16, Batch: 320/757, Loss: 0.6327, Time: 4.75s Epoch: 16, Batch: 330/757, Loss: 0.3154, Time: 4.75s Epoch: 16, Batch: 340/757, Loss: 0.7077, Time: 4.76s Epoch: 16, Batch: 350/757, Loss: 0.5217, Time: 4.75s Epoch: 16, Batch: 360/757, Loss: 0.6863, Time: 4.75s Epoch: 16, Batch: 370/757, Loss: 0.4821, Time: 4.75s Epoch: 16, Batch: 380/757, Loss: 0.4419, Time: 4.74s Epoch: 16, Batch: 390/757, Loss: 0.3508, Time: 4.75s Epoch: 16, Batch: 400/757, Loss: 0.5990, Time: 4.75s Epoch: 16, Batch: 410/757, Loss: 0.4705, Time: 4.74s Epoch: 16, Batch: 420/757, Loss: 0.4423, Time: 4.75s Epoch: 16, Batch: 430/757, Loss: 0.2702, Time: 4.74s Epoch: 16, Batch: 440/757, Loss: 0.4700, Time: 4.75s Epoch: 16, Batch: 450/757, Loss: 0.3036, Time: 4.75s Epoch: 16, Batch: 460/757, Loss: 0.4087, Time: 4.75s Epoch: 16, Batch: 470/757, Loss: 0.3120, Time: 4.75s Epoch: 16, Batch: 480/757, Loss: 0.2789, Time: 4.75s Epoch: 16, Batch: 490/757, Loss: 0.8945, Time: 4.76s Epoch: 16, Batch: 500/757, Loss: 0.6228, Time: 4.76s Epoch: 16, Batch: 510/757, Loss: 0.2723, Time: 4.75s Epoch: 16, Batch: 520/757, Loss: 0.4854, Time: 4.75s Epoch: 16, Batch: 530/757, Loss: 0.3580, Time: 4.75s Epoch: 16, Batch: 540/757, Loss: 0.6134, Time: 4.75s Epoch: 16, Batch: 550/757, Loss: 0.5591, Time: 4.74s Epoch: 16, Batch: 560/757, Loss: 0.5763, Time: 4.76s Epoch: 16, Batch: 570/757, Loss: 0.5480, Time: 4.74s Epoch: 16, Batch: 580/757, Loss: 1.5338, Time: 4.75s Epoch: 16, Batch: 590/757, Loss: 0.5192, Time: 4.75s Epoch: 16, Batch: 600/757, Loss: 0.4215, Time: 4.74s Epoch: 16, Batch: 610/757, Loss: 0.4012, Time: 4.74s Epoch: 16, Batch: 620/757, Loss: 0.4360, Time: 4.74s Epoch: 16, Batch: 630/757, Loss: 0.4266, Time: 4.74s Epoch: 16, Batch: 640/757, Loss: 0.6010, Time: 4.75s Epoch: 16, Batch: 650/757, Loss: 0.3302, Time: 4.73s Epoch: 16, Batch: 660/757, Loss: 0.2550, Time: 4.74s Epoch: 16, Batch: 670/757, Loss: 0.3891, Time: 4.74s Epoch: 16, Batch: 680/757, Loss: 0.6735, Time: 4.74s Epoch: 16, Batch: 690/757, Loss: 0.6507, Time: 4.74s Epoch: 16, Batch: 700/757, Loss: 0.4512, Time: 4.75s Epoch: 16, Batch: 710/757, Loss: 0.7065, Time: 4.74s Epoch: 16, Batch: 720/757, Loss: 0.3690, Time: 4.75s Epoch: 16, Batch: 730/757, Loss: 0.3536, Time: 4.74s Epoch: 16, Batch: 740/757, Loss: 0.4045, Time: 4.75s Epoch: 16, Batch: 750/757, Loss: 0.2761, Time: 4.75s Epoch 17/20: Train Loss: 0.5248, Val Loss: 0.5308, Val IoU: 0.3292, Val Dice: 0.3686 Epoch: 17, Batch: 0/757, Loss: 0.4489, Time: 0.85s Epoch: 17, Batch: 10/757, Loss: 0.4763, Time: 4.74s Epoch: 17, Batch: 20/757, Loss: 0.4543, Time: 4.75s Epoch: 17, Batch: 30/757, Loss: 0.6253, Time: 4.74s Epoch: 17, Batch: 40/757, Loss: 0.4566, Time: 4.75s Epoch: 17, Batch: 50/757, Loss: 0.3746, Time: 4.76s Epoch: 17, Batch: 60/757, Loss: 0.3573, Time: 4.75s Epoch: 17, Batch: 70/757, Loss: 0.3924, Time: 4.75s Epoch: 17, Batch: 80/757, Loss: 0.3131, Time: 4.75s Epoch: 17, Batch: 90/757, Loss: 0.4208, Time: 4.75s Epoch: 17, Batch: 100/757, Loss: 0.5949, Time: 4.75s Epoch: 17, Batch: 110/757, Loss: 0.7057, Time: 4.74s Epoch: 17, Batch: 120/757, Loss: 0.4382, Time: 4.75s Epoch: 17, Batch: 130/757, Loss: 0.4537, Time: 4.75s Epoch: 17, Batch: 140/757, Loss: 0.6235, Time: 4.74s Epoch: 17, Batch: 150/757, Loss: 0.4294, Time: 4.75s Epoch: 17, Batch: 160/757, Loss: 0.4518, Time: 4.75s Epoch: 17, Batch: 170/757, Loss: 0.3411, Time: 4.74s Epoch: 17, Batch: 180/757, Loss: 0.6058, Time: 4.75s Epoch: 17, Batch: 190/757, Loss: 0.4478, Time: 4.75s Epoch: 17, Batch: 200/757, Loss: 0.3661, Time: 4.75s Epoch: 17, Batch: 210/757, Loss: 0.4447, Time: 4.75s Epoch: 17, Batch: 220/757, Loss: 0.4595, Time: 4.74s Epoch: 17, Batch: 230/757, Loss: 0.6429, Time: 4.75s Epoch: 17, Batch: 240/757, Loss: 0.3993, Time: 4.75s Epoch: 17, Batch: 250/757, Loss: 0.3789, Time: 4.74s Epoch: 17, Batch: 260/757, Loss: 0.4924, Time: 4.75s Epoch: 17, Batch: 270/757, Loss: 0.3432, Time: 4.74s Epoch: 17, Batch: 280/757, Loss: 0.5317, Time: 4.74s Epoch: 17, Batch: 290/757, Loss: 0.4503, Time: 4.74s Epoch: 17, Batch: 300/757, Loss: 0.3256, Time: 4.74s Epoch: 17, Batch: 310/757, Loss: 0.5543, Time: 4.74s Epoch: 17, Batch: 320/757, Loss: 0.6276, Time: 4.74s Epoch: 17, Batch: 330/757, Loss: 0.5756, Time: 4.74s Epoch: 17, Batch: 340/757, Loss: 0.5981, Time: 4.74s Epoch: 17, Batch: 350/757, Loss: 0.2950, Time: 4.75s Epoch: 17, Batch: 360/757, Loss: 0.2898, Time: 4.75s Epoch: 17, Batch: 370/757, Loss: 0.4999, Time: 4.74s Epoch: 17, Batch: 380/757, Loss: 0.5688, Time: 4.75s Epoch: 17, Batch: 390/757, Loss: 0.4921, Time: 4.75s Epoch: 17, Batch: 400/757, Loss: 0.2757, Time: 4.75s Epoch: 17, Batch: 410/757, Loss: 0.2856, Time: 4.75s Epoch: 17, Batch: 420/757, Loss: 0.7913, Time: 4.74s Epoch: 17, Batch: 430/757, Loss: 0.2419, Time: 4.74s Epoch: 17, Batch: 440/757, Loss: 0.7583, Time: 4.75s Epoch: 17, Batch: 450/757, Loss: 0.3879, Time: 4.74s Epoch: 17, Batch: 460/757, Loss: 0.3664, Time: 4.74s Epoch: 17, Batch: 470/757, Loss: 0.6035, Time: 4.75s Epoch: 17, Batch: 480/757, Loss: 0.7734, Time: 4.73s Epoch: 17, Batch: 490/757, Loss: 0.3970, Time: 4.75s Epoch: 17, Batch: 500/757, Loss: 0.8216, Time: 4.74s Epoch: 17, Batch: 510/757, Loss: 0.4504, Time: 4.74s Epoch: 17, Batch: 520/757, Loss: 0.2849, Time: 4.75s Epoch: 17, Batch: 530/757, Loss: 0.4946, Time: 4.75s Epoch: 17, Batch: 540/757, Loss: 0.3382, Time: 4.74s Epoch: 17, Batch: 550/757, Loss: 0.6216, Time: 4.74s Epoch: 17, Batch: 560/757, Loss: 0.2918, Time: 4.74s Epoch: 17, Batch: 570/757, Loss: 0.2423, Time: 4.74s Epoch: 17, Batch: 580/757, Loss: 0.3271, Time: 4.75s Epoch: 17, Batch: 590/757, Loss: 0.5647, Time: 4.75s Epoch: 17, Batch: 600/757, Loss: 0.5450, Time: 4.74s Epoch: 17, Batch: 610/757, Loss: 0.4455, Time: 4.75s Epoch: 17, Batch: 620/757, Loss: 0.4594, Time: 4.75s Epoch: 17, Batch: 630/757, Loss: 1.1767, Time: 4.75s Epoch: 17, Batch: 640/757, Loss: 0.4733, Time: 4.74s Epoch: 17, Batch: 650/757, Loss: 0.4326, Time: 4.75s Epoch: 17, Batch: 660/757, Loss: 0.4212, Time: 4.74s Epoch: 17, Batch: 670/757, Loss: 0.2413, Time: 4.73s Epoch: 17, Batch: 680/757, Loss: 0.4710, Time: 4.74s Epoch: 17, Batch: 690/757, Loss: 0.5658, Time: 4.74s Epoch: 17, Batch: 700/757, Loss: 0.3678, Time: 4.74s Epoch: 17, Batch: 710/757, Loss: 0.8054, Time: 4.74s Epoch: 17, Batch: 720/757, Loss: 0.3096, Time: 4.73s Epoch: 17, Batch: 730/757, Loss: 0.9174, Time: 4.74s Epoch: 17, Batch: 740/757, Loss: 0.8401, Time: 4.74s Epoch: 17, Batch: 750/757, Loss: 0.3652, Time: 4.74s Epoch 18/20: Train Loss: 0.5180, Val Loss: 0.5489, Val IoU: 0.3194, Val Dice: 0.3600 Epoch: 18, Batch: 0/757, Loss: 0.2866, Time: 0.87s Epoch: 18, Batch: 10/757, Loss: 0.5855, Time: 4.73s Epoch: 18, Batch: 20/757, Loss: 0.4863, Time: 4.72s Epoch: 18, Batch: 30/757, Loss: 0.8463, Time: 4.73s Epoch: 18, Batch: 40/757, Loss: 0.3467, Time: 4.73s Epoch: 18, Batch: 50/757, Loss: 0.6821, Time: 4.74s Epoch: 18, Batch: 60/757, Loss: 0.6810, Time: 4.74s Epoch: 18, Batch: 70/757, Loss: 0.5476, Time: 4.74s Epoch: 18, Batch: 80/757, Loss: 0.3361, Time: 4.74s Epoch: 18, Batch: 90/757, Loss: 1.0151, Time: 4.73s Epoch: 18, Batch: 100/757, Loss: 0.6025, Time: 4.74s Epoch: 18, Batch: 110/757, Loss: 0.6330, Time: 4.74s Epoch: 18, Batch: 120/757, Loss: 0.4685, Time: 4.74s Epoch: 18, Batch: 130/757, Loss: 0.3753, Time: 4.73s Epoch: 18, Batch: 140/757, Loss: 0.5419, Time: 4.73s Epoch: 18, Batch: 150/757, Loss: 0.5349, Time: 4.73s Epoch: 18, Batch: 160/757, Loss: 0.2526, Time: 4.73s Epoch: 18, Batch: 170/757, Loss: 0.3662, Time: 4.73s Epoch: 18, Batch: 180/757, Loss: 0.2718, Time: 4.72s Epoch: 18, Batch: 190/757, Loss: 0.5542, Time: 4.72s Epoch: 18, Batch: 200/757, Loss: 0.4982, Time: 4.72s Epoch: 18, Batch: 210/757, Loss: 0.5267, Time: 4.72s Epoch: 18, Batch: 220/757, Loss: 0.3105, Time: 4.72s Epoch: 18, Batch: 230/757, Loss: 0.3360, Time: 4.72s Epoch: 18, Batch: 240/757, Loss: 0.4882, Time: 4.72s Epoch: 18, Batch: 250/757, Loss: 0.3368, Time: 4.72s Epoch: 18, Batch: 260/757, Loss: 0.2455, Time: 4.72s Epoch: 18, Batch: 270/757, Loss: 0.5484, Time: 4.72s Epoch: 18, Batch: 280/757, Loss: 0.4218, Time: 4.72s Epoch: 18, Batch: 290/757, Loss: 0.6328, Time: 4.72s Epoch: 18, Batch: 300/757, Loss: 0.5880, Time: 4.72s Epoch: 18, Batch: 310/757, Loss: 0.3727, Time: 4.72s Epoch: 18, Batch: 320/757, Loss: 0.4335, Time: 4.72s Epoch: 18, Batch: 330/757, Loss: 0.4757, Time: 4.72s Epoch: 18, Batch: 340/757, Loss: 0.5101, Time: 4.72s Epoch: 18, Batch: 350/757, Loss: 0.2216, Time: 4.72s Epoch: 18, Batch: 360/757, Loss: 0.5658, Time: 4.72s Epoch: 18, Batch: 370/757, Loss: 0.2855, Time: 4.72s Epoch: 18, Batch: 380/757, Loss: 0.3358, Time: 4.72s Epoch: 18, Batch: 390/757, Loss: 0.6708, Time: 4.72s Epoch: 18, Batch: 400/757, Loss: 0.4394, Time: 4.72s Epoch: 18, Batch: 410/757, Loss: 0.3225, Time: 4.72s Epoch: 18, Batch: 420/757, Loss: 0.5307, Time: 4.72s Epoch: 18, Batch: 430/757, Loss: 0.5442, Time: 4.72s Epoch: 18, Batch: 440/757, Loss: 0.5650, Time: 4.72s Epoch: 18, Batch: 450/757, Loss: 0.3788, Time: 4.72s Epoch: 18, Batch: 460/757, Loss: 0.9088, Time: 4.72s Epoch: 18, Batch: 470/757, Loss: 0.4012, Time: 4.72s Epoch: 18, Batch: 480/757, Loss: 0.4541, Time: 4.73s Epoch: 18, Batch: 490/757, Loss: 0.6445, Time: 4.72s Epoch: 18, Batch: 500/757, Loss: 1.0317, Time: 4.72s Epoch: 18, Batch: 510/757, Loss: 0.4674, Time: 4.72s Epoch: 18, Batch: 520/757, Loss: 0.6170, Time: 4.72s Epoch: 18, Batch: 530/757, Loss: 0.3482, Time: 4.72s Epoch: 18, Batch: 540/757, Loss: 0.5334, Time: 4.72s Epoch: 18, Batch: 550/757, Loss: 0.5370, Time: 4.73s Epoch: 18, Batch: 560/757, Loss: 0.5940, Time: 4.72s Epoch: 18, Batch: 570/757, Loss: 0.2794, Time: 4.72s Epoch: 18, Batch: 580/757, Loss: 0.2608, Time: 4.73s Epoch: 18, Batch: 590/757, Loss: 0.4431, Time: 4.73s Epoch: 18, Batch: 600/757, Loss: 0.5482, Time: 4.73s Epoch: 18, Batch: 610/757, Loss: 0.6433, Time: 4.73s Epoch: 18, Batch: 620/757, Loss: 0.7358, Time: 4.73s Epoch: 18, Batch: 630/757, Loss: 0.3550, Time: 4.73s Epoch: 18, Batch: 640/757, Loss: 0.4309, Time: 4.74s Epoch: 18, Batch: 650/757, Loss: 0.2184, Time: 4.73s Epoch: 18, Batch: 660/757, Loss: 0.4445, Time: 4.73s Epoch: 18, Batch: 670/757, Loss: 0.3702, Time: 4.74s Epoch: 18, Batch: 680/757, Loss: 0.4239, Time: 4.74s Epoch: 18, Batch: 690/757, Loss: 0.5641, Time: 4.73s Epoch: 18, Batch: 700/757, Loss: 0.4172, Time: 4.74s Epoch: 18, Batch: 710/757, Loss: 0.5575, Time: 4.75s Epoch: 18, Batch: 720/757, Loss: 0.4137, Time: 4.75s Epoch: 18, Batch: 730/757, Loss: 0.2484, Time: 4.74s Epoch: 18, Batch: 740/757, Loss: 0.4489, Time: 4.74s Epoch: 18, Batch: 750/757, Loss: 0.8791, Time: 4.74s Epoch 19/20: Train Loss: 0.5135, Val Loss: 0.5296, Val IoU: 0.3339, Val Dice: 0.3729 Epoch: 19, Batch: 0/757, Loss: 0.3265, Time: 0.85s Epoch: 19, Batch: 10/757, Loss: 0.4323, Time: 4.74s Epoch: 19, Batch: 20/757, Loss: 0.3994, Time: 4.73s Epoch: 19, Batch: 30/757, Loss: 0.5520, Time: 4.74s Epoch: 19, Batch: 40/757, Loss: 0.2722, Time: 4.74s Epoch: 19, Batch: 50/757, Loss: 0.5104, Time: 4.74s Epoch: 19, Batch: 60/757, Loss: 0.2289, Time: 4.74s Epoch: 19, Batch: 70/757, Loss: 0.5780, Time: 4.74s Epoch: 19, Batch: 80/757, Loss: 0.5517, Time: 4.73s Epoch: 19, Batch: 90/757, Loss: 0.4730, Time: 4.73s Epoch: 19, Batch: 100/757, Loss: 0.4313, Time: 4.73s Epoch: 19, Batch: 110/757, Loss: 0.6655, Time: 4.74s Epoch: 19, Batch: 120/757, Loss: 0.9113, Time: 4.74s Epoch: 19, Batch: 130/757, Loss: 0.3427, Time: 4.74s Epoch: 19, Batch: 140/757, Loss: 0.4250, Time: 4.73s Epoch: 19, Batch: 150/757, Loss: 0.2361, Time: 4.74s Epoch: 19, Batch: 160/757, Loss: 0.6210, Time: 4.74s Epoch: 19, Batch: 170/757, Loss: 0.3330, Time: 4.75s Epoch: 19, Batch: 180/757, Loss: 0.3690, Time: 4.74s Epoch: 19, Batch: 190/757, Loss: 0.4303, Time: 4.74s Epoch: 19, Batch: 200/757, Loss: 0.3089, Time: 4.74s Epoch: 19, Batch: 210/757, Loss: 0.2922, Time: 4.74s Epoch: 19, Batch: 220/757, Loss: 0.3937, Time: 4.74s Epoch: 19, Batch: 230/757, Loss: 0.6347, Time: 4.74s Epoch: 19, Batch: 240/757, Loss: 0.6557, Time: 4.74s Epoch: 19, Batch: 250/757, Loss: 0.3366, Time: 4.74s Epoch: 19, Batch: 260/757, Loss: 0.7007, Time: 4.74s Epoch: 19, Batch: 270/757, Loss: 0.8020, Time: 4.75s Epoch: 19, Batch: 280/757, Loss: 0.5624, Time: 4.74s Epoch: 19, Batch: 290/757, Loss: 0.4627, Time: 4.74s Epoch: 19, Batch: 300/757, Loss: 0.4268, Time: 4.74s Epoch: 19, Batch: 310/757, Loss: 0.3433, Time: 4.73s Epoch: 19, Batch: 320/757, Loss: 0.3966, Time: 4.74s Epoch: 19, Batch: 330/757, Loss: 0.3949, Time: 4.74s Epoch: 19, Batch: 340/757, Loss: 0.4771, Time: 4.74s Epoch: 19, Batch: 350/757, Loss: 0.4745, Time: 4.75s Epoch: 19, Batch: 360/757, Loss: 0.4077, Time: 4.73s Epoch: 19, Batch: 370/757, Loss: 0.4312, Time: 4.74s Epoch: 19, Batch: 380/757, Loss: 0.5451, Time: 4.73s Epoch: 19, Batch: 390/757, Loss: 0.2995, Time: 4.74s Epoch: 19, Batch: 400/757, Loss: 0.3973, Time: 4.74s Epoch: 19, Batch: 410/757, Loss: 0.7510, Time: 4.73s Epoch: 19, Batch: 420/757, Loss: 0.4580, Time: 4.73s Epoch: 19, Batch: 430/757, Loss: 0.4723, Time: 4.73s Epoch: 19, Batch: 440/757, Loss: 0.8047, Time: 4.74s Epoch: 19, Batch: 450/757, Loss: 0.4188, Time: 4.75s Epoch: 19, Batch: 460/757, Loss: 0.6062, Time: 4.74s Epoch: 19, Batch: 470/757, Loss: 0.5510, Time: 4.74s Epoch: 19, Batch: 480/757, Loss: 0.8917, Time: 4.74s Epoch: 19, Batch: 490/757, Loss: 0.3950, Time: 4.75s Epoch: 19, Batch: 500/757, Loss: 0.3659, Time: 4.75s Epoch: 19, Batch: 510/757, Loss: 0.4640, Time: 4.74s Epoch: 19, Batch: 520/757, Loss: 1.4742, Time: 4.74s Epoch: 19, Batch: 530/757, Loss: 0.4507, Time: 4.75s Epoch: 19, Batch: 540/757, Loss: 0.3166, Time: 4.76s Epoch: 19, Batch: 550/757, Loss: 0.4015, Time: 4.75s Epoch: 19, Batch: 560/757, Loss: 0.4535, Time: 4.76s Epoch: 19, Batch: 570/757, Loss: 0.3919, Time: 4.76s Epoch: 19, Batch: 580/757, Loss: 0.6242, Time: 4.76s Epoch: 19, Batch: 590/757, Loss: 0.2898, Time: 4.75s Epoch: 19, Batch: 600/757, Loss: 0.4394, Time: 4.76s Epoch: 19, Batch: 610/757, Loss: 0.3210, Time: 4.75s Epoch: 19, Batch: 620/757, Loss: 0.5536, Time: 4.75s Epoch: 19, Batch: 630/757, Loss: 0.3506, Time: 4.75s Epoch: 19, Batch: 640/757, Loss: 0.5930, Time: 4.76s Epoch: 19, Batch: 650/757, Loss: 0.4764, Time: 4.76s Epoch: 19, Batch: 660/757, Loss: 0.4275, Time: 4.75s Epoch: 19, Batch: 670/757, Loss: 0.4602, Time: 4.76s Epoch: 19, Batch: 680/757, Loss: 0.3632, Time: 4.76s Epoch: 19, Batch: 690/757, Loss: 0.6236, Time: 4.76s Epoch: 19, Batch: 700/757, Loss: 0.3257, Time: 4.75s Epoch: 19, Batch: 710/757, Loss: 0.5709, Time: 4.75s Epoch: 19, Batch: 720/757, Loss: 0.3961, Time: 4.75s Epoch: 19, Batch: 730/757, Loss: 0.6074, Time: 4.75s Epoch: 19, Batch: 740/757, Loss: 0.2825, Time: 4.75s Epoch: 19, Batch: 750/757, Loss: 0.5569, Time: 4.75s Epoch 20/20: Train Loss: 0.5218, Val Loss: 0.5014, Val IoU: 0.3303, Val Dice: 0.3693 Training complete! Best IoU: 0.3409 Models saved to /content/tiles/unet_models Training curves saved to /content/tiles/unet_models/training_curves.png
We can check the Loss, IoU and Dice Score metrics:
In [ ]:
geoai.plot_performance_metrics(
history_path=f"{out_folder}/unet_models/training_history.pth",
figsize=(15, 5),
verbose=True,
)
Best IoU: 0.3409 Best Dice: 0.3806 Final IoU: 0.3303 Final Dice: 0.3693
Then we apply the trained model to a test image:
In [ ]:
test_raster_path = '/content/drive/MyDrive/Datasets/Naip_chesapeak/naip_images/m_3807511_se_18_060_20181104.tif'
masks_path = "naip_test_semantic_prediction.tif"
model_path = f"{out_folder}/unet_models/best_model.pth"
In [ ]:
geoai.semantic_segmentation(
input_path=test_raster_path,
output_path=masks_path,
model_path=model_path,
architecture="unet",
encoder_name="resnet34",
num_channels=4,
num_classes=13,
window_size=512,
overlap=256,
batch_size=4,
)
Input file format: GeoTIFF (.tif) Processing 1911 windows...
2000it [01:21, 24.50it/s]
Predicted classes: 7 classes, Background: 0.0% Inference completed in 152.65 seconds Saved prediction to naip_test_semantic_prediction.tif
We visualize the result:
In [ ]:
geoai.write_colormap(masks_path, train_mask, output=masks_path)
In [ ]:
m = leafmap.Map()
m.add_raster(masks_path, cmap='inferno', layer_name="Mask")
m
Map(center=[38.7814955, -75.6560255], controls=(ZoomControl(options=['position', 'zoom_in_text', 'zoom_in_titl…