![]() RUN wget $CV_VERSION.zip -O opencv.zip & \ # OpenCV Contrib : wget -quiet -O opencv_contrib.zip # OpenCV 3.4.7 : wget -quiet -O opencv.zip $CONDA_HOME/etc/profile.d/conda.sh" > $HOME/.bashrc & \Įcho "conda activate pydev" > $HOME/.bashrcĮNV PATH=$CONDA_HOME/envs/pydev/bin:$PATH RUN conda update -y conda & conda init bash & \Ĭonda config -env -set always_yes true & \Ĭonda create -y -n pydev Python=3.7 pip tqdm pandas \Įcho ". Libswscale-dev zlib1g-dev libopenexr-dev \ Libjpeg-dev libpng-dev libtiff-dev edisplay \ Libavformat-dev libavcodec-dev libavfilter-dev \ Libcanberra-gtk-module libcanberra-gtk3-module \ X11-apps libxext-dev libxrender-dev libxtst-dev \ ![]() Git net-tools vim tmux rsync sudo less cmake \ RUN apt-get update & apt-get install -y -qq firefox git \īuild-essential tar wget bzip2 unzip curl \ Install="docker run -rm -it -gpus all -privileged -net=host -ipc=host -e DISPLAY=$DISPLAY -v /tmp/.X11-unix:/tmp/.X11-unix -volume=$PWD:/home/jdoe/workspace -p 58080:8080 -name ubuntu-dev ubuntu-dev:cuda10.1-ubuntu18 bash" Next: Using the Tersnorrtx github repository which has many other models/implementationsįROM nvidia/cuda:10.1-cudnn7-devel-ubuntu18.04īuild="DOCKER_BUILDKIT=1 docker build -rm -f -t ubuntu-dev:cuda10.1-ubuntu18. Saved image with bounding boxes of detected objects to dog_bboxes.png. Loading ONNX file from path yolov3.onnx.īuilding an engine from file yolov3.onnx this may take a while. Load yolov3.onnx and do the inference $ python onnx_to_tensorrt.py Downloading from, this may take a while.ġ00% 163759 / 163759 # install packages separately while maintaining numpy=1.7.1ĭownload & convert “yolov3.cfg” and “yolov3.weights” to “yolov3.onnx” model $ python2 yolov3_to_onnx.py Downloading from, this may take a while.ġ00% 8342 / 8342ĭownloading from, this may take a while.ġ00% 248007048 / 248007048 ![]() # In case of error remove the P圜UDA dependencies ![]() It appears that the yolov3_to_onnx.py works only with Python2 as of now so will need pip2 packages $ cd $HOME/install/TensorRT-5.1.5/samples/python/yolov3_onnx Look for samples in the NVIDIA TensorRT Documentation $ python configure.py -cuda-root=/usr/local/cuda -cxxflags=-std=c++11 Setup P圜uda (Do this config/install for Python2 and Python3) $ conda create -quiet -n testyv3 cudatoolkit=10.1 To obtain the various python binary builds, download the TensorRT 5.1.5.0 GA for CentOS/RedHat 7 and CUDA 10.1 tar package Mamba install jupyterlab voila ipywidgets pandas matplotlib 5. Python in WSL2 Miniconda mkdir -p ~/dev/miniconda3/īash ~/dev/miniconda3/miniconda.sh -b -u -p ~/dev/miniconda3īash Install Mamba for simpler package management conda install mamba -n base -c conda-forge Restart the WSL2 instance and test for docker run PS C:\Users\rahul> wsl -shutdownĭocker-desktop Running 2 4. Sudo apt-get -y install cuda-toolkit-11-8 CUDA toolkit for development in WSL2 CUDA 11.8 Installation wget Install WSL2 with the Ubuntu GUI wsl -list -onlineĢ.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |