detectron2
detectron2 copied to clipboard
detectron2 windows build
## Run command python demo.py --config-file ../configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml --video-input test.mp4 --opts MODEL.WEIGHTS detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl ## Expected behavior When running demo.py, the GPU is not used, but the CPU is used  ##...
I tried putting the whole log in, but it was too long. Here's the ending error message: ``` C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Auxiliary\Build\detectron2\detectron2\layers\csrc\box_iou_rotated\box_iou_rotated_cpu.cpp : fatal error C1083: Cannot open compiler...
Installing the latest version of fvcore results in the following error: https://github.com/facebookresearch/detectron2/issues/2652 We should specify the solution, which is rolling fvcore to one of the previous versions, in the README...
(ts_env) D:\project\public\detectron2>python setup.py build develop running build running build_py running build_ext building 'detectron2._C' extension Emitting ninja build file D:\project\public\detectron2\build\temp.win-amd64-3.7\Release\build.ninja... Compiling objects... Allowing ninja to set a default number of workers......
I am building the project by running pip install -e detectron2. However I encountered this error. ``` ERROR: Command errored out with exit status 1: command: 'C:\Users\Deployment\.conda\envs\sliding_windows_py37_copy\python.exe' -c 'import sys,...
## ❓ Questions and Help If you do not know the root cause of the problem / bug, and wish someone to help you, please [1/6] C:\Program Files\NVIDIA GPU Computing...
This way I'm able to build and instal detectron2 on Windows 10.. I use CPU only for pytorch. conda create -n test conda activate test conda install pip opencv numpy...
I am using a windows 10 machine with the following configuration NVIDIA GeForce GTX 1650Ti miniconda3 python 3.8 CUDA 11.1 PyTorch 1.8 downloaded directly & installed from PyTorch.org for CUDA-11.1...
## ❓ Questions and Help python: 3.6.0 torch: 1.7.0 the problem was shown as this: FAILED: D:/GitHub/LocalFiles/detectron2/build/temp.win-amd64-3.6/Release/GitHub/LocalFiles/detectron2/detectron2/layers/csrc/deformable/deform_conv_cuda.obj and the detail is this: D:/Anaconda3/envs/mainenv/lib/site-packages/torch/include\torch/csrc/jit/ir/ir.h(1347): error: member "torch::jit::ProfileOptionalOp::Kind" may not be initialized...
**Requirements:** - **Python 3.6.1** - **Pytorch 1.4.0** - **torchvision 0.5** - **fvcore:** `pip install git+https://github.com/facebookresearch/fvcore` - **pycocotools:** `pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI` - **VS2019/CUDA10.1** **Procedures** - **Step1:** `git clone https://github.com/conansherry/detectron2.git` - **Step2:**...