updated CUDA to version 10 (#1138)

* updated CUDA to version 10 * updated tensorflow * added comment about NVIDIA_REQUIRE_CUDA env varOF
cvat-ai · Feb 12, 2020 · fccccab · fccccab
1 parent d9fe712
commit fccccab
Show file tree

Hide file tree

Showing 4 changed files with 20 additions and 14 deletions.
diff --git a/components/cuda/docker-compose.cuda.yml b/components/cuda/docker-compose.cuda.yml
@@ -15,4 +15,9 @@ services:
     environment:
       NVIDIA_VISIBLE_DEVICES: all
       NVIDIA_DRIVER_CAPABILITIES: compute,utility
-      NVIDIA_REQUIRE_CUDA: "cuda>=9.0"
+      # That environment variable is used by the Nvidia Container Runtime.
+      # The Nvidia Container Runtime parses this as:
+      #   :space:: logical OR
+      #   ,: Logical AND
+      # https://gitlab.com/nvidia/container-images/cuda/issues/31#note_149432780
+      NVIDIA_REQUIRE_CUDA: "cuda>=10.0 brand=tesla,driver>=384,driver<385 brand=tesla,driver>=410,driver<411"
diff --git a/components/cuda/install.sh b/components/cuda/install.sh
@@ -14,24 +14,25 @@ echo "$NVIDIA_GPGKEY_SUM  cudasign.pub" | sha256sum -c --strict - && rm cudasign
 echo "deb http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64 /" > /etc/apt/sources.list.d/cuda.list && \
 echo "deb http://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1604/x86_64 /" > /etc/apt/sources.list.d/nvidia-ml.list
 
-CUDA_VERSION=9.0.176
-NCCL_VERSION=2.1.15
-CUDNN_VERSION=7.6.2.24
-CUDA_PKG_VERSION="9-0=${CUDA_VERSION}-1"
+CUDA_VERSION=10.0.130
+NCCL_VERSION=2.5.6
+CUDNN_VERSION=7.6.5.32
+CUDA_PKG_VERSION="10-0=$CUDA_VERSION-1"
 echo 'export PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:${PATH}' >> ${HOME}/.bashrc
 echo 'export LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:${LD_LIBRARY_PATH}' >> ${HOME}/.bashrc
 
 apt-get update && apt-get install -y --no-install-recommends --allow-unauthenticated \
-    libprotobuf-dev \
-    libprotoc-dev \
-    protobuf-compiler \
     cuda-cudart-$CUDA_PKG_VERSION \
+    cuda-compat-10-0 \
     cuda-libraries-$CUDA_PKG_VERSION \
-    libnccl2=$NCCL_VERSION-1+cuda9.0 \
-    libcudnn7=$CUDNN_VERSION-1+cuda9.0 && \
-    ln -s cuda-9.0 /usr/local/cuda && \
+    cuda-nvtx-$CUDA_PKG_VERSION \
+    libnccl2=$NCCL_VERSION-1+cuda10.0 \
+    libcudnn7=$CUDNN_VERSION-1+cuda10.0 && \
+    ln -s cuda-10.0 /usr/local/cuda && \
+    apt-mark hold libnccl2 libcudnn7  && \
     rm -rf /var/lib/apt/lists/* \
     /etc/apt/sources.list.d/nvidia-ml.list /etc/apt/sources.list.d/cuda.list
 
 python3 -m pip uninstall -y tensorflow
-python3 -m pip install --no-cache-dir tensorflow-gpu==1.13.1
+python3 -m pip install --no-cache-dir tensorflow-gpu==1.15.2
+
diff --git a/cvat/requirements/base.txt b/cvat/requirements/base.txt
@@ -39,7 +39,7 @@ django-rest-auth[with_social]==0.9.5
 cython==0.29.13
 matplotlib==3.0.3
 scikit-image==0.15.0
-tensorflow==1.13.1
+tensorflow==1.15.2
 keras==2.2.5
 opencv-python==4.1.0.25
 h5py==2.9.0

diff --git a/utils/tfrecords/requirements.txt b/utils/tfrecords/requirements.txt
@@ -1,3 +1,3 @@
 argparse==1.1
-tensorflow==1.13.1
+tensorflow==1.15.2
 pathlib==1.0.1