Merge branch 'master' into sarthakpati-patch-1

.devcontainer/onCreateCommand.sh

@@ -5,4 +5,4 @@ pip install wheel
 pip install openvino-dev==2023.0.1 # [OPTIONAL] to generate optimized models for inference
 pip install mlcube_docker          # [OPTIONAL] to deploy GaNDLF models as MLCube-compliant Docker containers
 pip install medmnist==2.1.0
-pip install torch==1.13.1+cpu torchvision==0.14.1+cpu torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cpu
+pip install torch==2.1.0+cpu torchvision==0.16.0+cpu torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cpu

.devcontainer/postCreateCommand.sh

@@ -6,7 +6,7 @@
 # if runnning on a GPU machine, install the GPU version of pytorch
 if command -v nvidia-smi &> /dev/null
 then
-	pip install torch==1.13.1+cu116 torchvision==0.14.1+cu116 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu116
+	pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu118
 fi
 
 pip install -e .

.github/workflows/docker-image.yml

@@ -25,8 +25,8 @@ jobs:
       fail-fast: false # So that remaining jobs don't instantly quit if one fails (e.g, CPU/ROCm don't upload if CUDA just fails to push to ghcr...)
       matrix:
         include: # Platform locates Dockerfile ("Dockerfile-{PLATFORM}"), docker tag has to be all lowercase alphanumeric for mysterious docker reasons
-          - platform: CUDA11.6
-            dockertag: cuda116
+          - platform: CUDA11.8
+            dockertag: cuda118
           - platform: CPU
             dockertag: cpu
           # - platform: ROCm

.github/workflows/mlcube-test.yml

@@ -73,7 +73,7 @@ jobs:
         python -m pip install --upgrade pip
         python -m pip install wheel
         python -m pip install openvino-dev==2023.0.1 mlcube_docker
-        pip install torch==1.13.1+cpu torchvision==0.14.1+cpu torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cpu
+        pip install torch==2.1.0+cpu torchvision==0.16.0+cpu torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cpu
         pip install -e .
     - name: Run mlcube deploy tests
       working-directory: ./testing

.github/workflows/openfl-test.yml

@@ -73,7 +73,7 @@ jobs:
         sudo apt-get install libvips libvips-tools -y
         python -m pip install --upgrade pip
         python -m pip install wheel
-        pip install torch==1.13.1+cpu torchvision==0.14.1+cpu torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cpu
+        pip install torch==2.1.0+cpu torchvision==0.16.0+cpu torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cpu
         pip install -e .
     - name: Run generic unit tests to download data and construct CSVs
       if: steps.changed-files-specific.outputs.only_modified == 'false' # Run on any non-docs change

.github/workflows/python-test.yml

@@ -74,7 +74,7 @@ jobs:
         python -m pip install --upgrade pip
         python -m pip install wheel
         python -m pip install openvino-dev==2023.0.1 mlcube_docker
-        pip install torch==1.13.1+cpu torchvision==0.14.1+cpu torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cpu
+        pip install torch==2.1.0+cpu torchvision==0.16.0+cpu torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cpu
         pip install -e .
     - name: Run generic unit tests
       if: steps.changed-files-specific.outputs.only_modified == 'false' # Run on any non-docs change

Dockerfile-CPU

@@ -9,7 +9,7 @@ RUN add-apt-repository ppa:deadsnakes/ppa
 RUN apt-get update &&  apt-get install -y  python3.9 python3-pip libjpeg8-dev zlib1g-dev python3-dev libpython3.9-dev libffi-dev libgl1
 RUN python3.9 -m pip install --upgrade pip
 # EXPLICITLY install cpu versions of torch/torchvision (not all versions have +cpu modes on PyPI...)
-RUN python3.9 -m pip install torch==1.13.1+cpu torchvision==0.14.1+cpu torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cpu
+RUN python3.9 -m pip install torch==2.1.0+cpu torchvision==0.16.0+cpu torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cpu
 RUN python3.9 -m pip install openvino-dev==2023.0.1 opencv-python-headless mlcube_docker
 
 # Do some dependency installation separately here to make layer caching more efficient

Dockerfile-CUDA11.6 → Dockerfile-CUDA11.8

@@ -1,4 +1,4 @@
-FROM nvidia/cuda:11.6.2-devel-ubuntu20.04
+FROM nvidia/cuda:11.8.0-devel-ubuntu20.04
 LABEL github="https://github.com/mlcommons/GaNDLF"
 LABEL docs="https://mlcommons.github.io/GaNDLF/"
 LABEL version=1.0
@@ -12,7 +12,7 @@ RUN apt-get update && apt-get install -y software-properties-common
 RUN add-apt-repository ppa:deadsnakes/ppa
 RUN apt-get update &&  apt-get install -y  python3.9 python3-pip libjpeg8-dev zlib1g-dev python3-dev libpython3.9-dev libffi-dev libgl1
 RUN python3.9 -m pip install --upgrade pip
-RUN python3.9 -m pip install torch==1.13.1+cu116 torchvision==0.14.1+cu116 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu116
+RUN python3.9 -m pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu118
 RUN python3.9 -m pip install openvino-dev==2023.0.1 opencv-python-headless mlcube_docker
 
 # Do some dependency installation separately here to make layer caching more efficient

Dockerfile-ROCm

@@ -1,4 +1,4 @@
-FROM rocm/pytorch:rocm5.2.3_ubuntu20.04_py3.7_pytorch_1.12.1
+FROM rocm/pytorch:rocm5.6_ubuntu20.04_py3.8_pytorch_1.12.1
 LABEL github="https://github.com/mlcommons/GaNDLF"
 LABEL docs="https://mlcommons.github.io/GaNDLF/"
 LABEL version=1.0
@@ -10,7 +10,7 @@ RUN apt-get update && apt-get install -y software-properties-common
 RUN add-apt-repository ppa:deadsnakes/ppa
 RUN apt-get update &&  apt-get install -y  python3.9 python3-pip libjpeg8-dev zlib1g-dev python3-dev libpython3.9-dev libffi-dev libgl1
 RUN python3.9 -m pip install --upgrade pip
-RUN python3.9 -m pip install torch==1.13.1+rocm5.2 torchvision==0.14.1+rocm5.2 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/rocm5.2
+RUN python3.9 -m pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/rocm5.6
 RUN python3.9 -m pip install --upgrade pip && python3.9 -m pip install openvino-dev==2023.0.1 opencv-python-headless mlcube_docker
 RUN apt-get update && apt-get install -y libgl1
 

docs/setup.md

@@ -30,11 +30,11 @@ GaNDLF's primary computational foundation is built on PyTorch, and as such it su
 (venv_gandlf) $> ### subsequent commands go here
 ### PyTorch installation - https://pytorch.org/get-started/previous-versions/#v210
 ## CUDA 11.6
-# (venv_gandlf) $> pip install torch==1.13.1+cu116 torchvision==0.14.1+cu116 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu116
+# (venv_gandlf) $> pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu118
 ## ROCm
-# (venv_gandlf) $> pip install torch==1.13.1+rocm5.2 torchvision==0.14.1+rocm5.2 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/rocm5.2
+# (venv_gandlf) $> pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/rocm5.6
 ## CPU-only
-# (venv_gandlf) $> pip install torch==1.13.1+cpu torchvision==0.14.1+cpu torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cpu
+# (venv_gandlf) $> pip install torch==2.1.0+cpu torchvision==0.16.0+cpu torchaudio==2.1.0 --extra-index-url https://download.pytorch.org/whl/cpu
 ```
 
 ### Optional Dependencies 

mlcube/model_mlcube/mlcube.yaml

@@ -30,7 +30,7 @@ docker:
   # Docker build context relative to $MLCUBE_ROOT. (gandlf_deploy can handle this automatically.)
   build_context: "../"
   # Docker file name within docker build context. Any "Dockerfile-*" in the GaNDLF source repo is valid.
-  build_file: "Dockerfile-CUDA11.6"
+  build_file: "Dockerfile-CUDA11.8"
 
   # These settings should be set by global MLCube configuration, generally not per-deployment.
   # However, some sane defaults (for Docker >19.03) are here:

setup.py

@@ -81,7 +81,7 @@ def run(self):
 
 
 requirements = [
-    "torch==1.13.1",
+    "torch==2.1.0",
     "black==23.11.0",
     "numpy==1.25.0",
     "scipy",