docker update

docker/Dockerfile2

@@ -0,0 +1,46 @@
+# Use an existing image as the base
+FROM nvcr.io/nvidia/pytorch:23.04-py3
+# FROM pytorch/pytorch:1.13.1-cuda11.6-cudnn8-devel
+# FROM pytorch/pytorch:2.0.0-cuda11.7-cudnn8-devel
+# 
+# Add the current user to the image
+ARG USER_NAME=lhunor
+ARG USER_ID=11017
+ARG GROUP_NAME=guest
+ARG GROUP_ID=11000
+
+# Update the system and install required packages
+RUN apt-get update && apt-get upgrade -y && apt-get install -y sudo git apt-utils htop
+
+# Create a new group with the same GID as the host
+RUN groupadd --gid $GROUP_ID $GROUP_NAME
+
+# Create a new user with the same UID and GID as the host
+RUN useradd --uid $USER_ID --gid $GROUP_ID --shell /bin/bash --create-home $USER_NAME
+
+# don't require password with sudo, for convenience
+# not the safest thing to do, but hopefully okay inside the container
+RUN echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
+
+# Add the new user to the sudo group
+RUN usermod -aG sudo $USER_NAME
+
+# Set the default user to the new user
+USER $USER_NAME
+
+WORKDIR /workspace
+
+ENV PATH="$PATH:/home/$USER_NAME/.local/bin"
+RUN pip install --upgrade pip
+COPY requirements.txt /tmp/
+RUN pip install --requirement /tmp/requirements.txt
+RUN pip install torch-cluster -f https://data.pyg.org/whl/torch-2.0.0+cu117.html
+
+
+# defining the volumes that will be mounted
+VOLUME [ "/data-net" ]
+VOLUME [ "/data-local" ]
+VOLUME [ "/home-net" ]
+
+# Start the container with a bash shell
+CMD ["/bin/bash"]

docker/docker-compose.yml

@@ -19,3 +19,24 @@ services:
         reservations:
           devices:
             - capabilities: [gpu]
+
+
+  lhunor_torch_2:
+    image: lhunor_torch:nv23.04
+    container_name: lhunor_torch_nv23.04
+    ipc: host
+    tty: true
+    ulimits:
+      memlock: -1
+      stack: 67108864
+    volumes:
+      - '/home-net/lhunor:/home-net'
+      - '/data-net/guest/lhunor/data:/data-net'
+      - '/data-fast/126-data1/lhunor/data:/data-local/126'
+      - '/data-fast/127-data1/lhunor/data:/data-local/127'
+      - '/data-fast/128-data1/lhunor/data:/data-local/128'
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - capabilities: [gpu]

docker/requirements.txt

@@ -1,3 +1,4 @@
+torch==2.0.0    
 numpy
 matplotlib
 opencv-python