update docker

docker/Dockerfile2

@@ -1,7 +1,7 @@
 # Use an existing image as the base
-FROM nvcr.io/nvidia/pytorch:23.04-py3
+# 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
+FROM pytorch/pytorch:2.0.1-cuda11.7-cudnn8-devel
 # 
 # Add the current user to the image
 ARG USER_NAME=lhunor
@@ -10,7 +10,7 @@ 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
+RUN apt-get update && 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
@@ -25,6 +25,12 @@ RUN echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
 # Add the new user to the sudo group
 RUN usermod -aG sudo $USER_NAME
 
+# install conda stuff still as root
+RUN conda update -n base conda
+RUN conda install -c fvcore -c iopath -c conda-forge fvcore iopath -y
+RUN conda install -c bottler nvidiacub -y
+RUN conda install pytorch3d -c pytorch3d -y
+
 # Set the default user to the new user
 USER $USER_NAME
 
@@ -33,8 +39,8 @@ 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
+RUN pip install --requirement /tmp/requirements.txt
 
 
 # defining the volumes that will be mounted

docker/docker-compose.yml

@@ -26,6 +26,28 @@ services:
     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/127-data2/lhunor/data:/data-local/127_2'
+      - '/data-fast/128-data1/lhunor/data:/data-local/128'
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - capabilities: [gpu]
+
+
+  lhunor_iccvw:
+    image: lhunor_iccvw:pt2.0.1
+    container_name: lhunor_iccvw_pt2.0.1
+    ipc: host
+    tty: true
     ulimits:
       memlock: -1
       stack: 67108864

docker/requirements.txt

@@ -1,13 +1,10 @@
-torch==2.0.0    
 numpy
-matplotlib
 opencv-python
 wandb
 scipy
 plotly
 pandas
 cmapy
-pytorch3d
 tables
 numpy-stl
 torchmetrics