安裝detectron2
python3.6，cuda10.1，
1 )? 安裝detectron2參考下面幾個文檔，
但出現(xiàn)RuntimeError:Not compiled with GPU support，一直沒解決(更改了detectron的clone方式和安裝方式不再出現(xiàn))，
便新建conda環(huán)境，使用第二種方法ok
https://blog.csdn.net/sophia_xw/article/details/102561410
conda create -n d2p36 python=3.6
source activate d2p36??// use every reboot
pip install -U torch torchvision
conda install -c menpo opencv3
pip install -U
'git+https://github.com/facebookresearch/fvcore'
pip install cython
pip install
'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
//git clone https://github.com/facebookresearch/detectron2detectron2_repo這個沒有試過
//pip install -e detectron2_repo
https://blog.csdn.net/jgj123321/article/details/105475027
git clone https://github.com/facebookresearch/detectron2.git?
cd detectron2
python -m pip install -e .
https://blog.csdn.net/m0_37709262/article/details/102732057? 也不行
//pip install'git+https://github.com/facebookresearch/detectron2.git'? //linux找不到被clone到哪里了
?//(add --user if youdon't have permission)
// Or, to install it from a local clone:
git clone https://github.com/facebookresearch/detectron2.git
cd detectron2 && pip install -e .
https://github.com/facebookresearch/detectron2/blob/master/INSTALL.md
//python -m pip install detectron2 -fhttps://dl.fbaipublicfiles.com/detectron2/wheels/cu101/index.html? //linux找不到被clone到哪里了
2)安裝參考這個，能正常運(yùn)行demo，
conda create -n dt2p36 python=3.6
source activate dt2p36??// use every reboot
https://www.aiuai.cn/aifarm1288.html
依次參考安裝依賴庫
...
方式二:
git clone https://github.com/facebookresearch/detectron2.git
cd detectron2
python -m pip install -e .
出現(xiàn)一些錯誤或有些庫使用的是python3.5的，用下面的命令更新解決
pip install -U torch torchvision
pip install -U torch pycocotools
pip install cython
3) demo腳本? 每次要重啟激活環(huán)境source activate dt2p36?? // use every reboot
原文鏈接：https://blog.csdn.net/sophia_xw/article/details/102561410
//python demo/demo.py --config-file
configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml --input 001.jpg
--output results --opts MODEL.WEIGHTS models/model_final_f10217.pkl
注意點(diǎn)：
測試圖片自己找，我的是000043.jpg，放在當(dāng)前工程自己新建的文件夾images中；
當(dāng)前工程下，新建results文件夾存儲結(jié)果圖片，我在服務(wù)器環(huán)境中，沒有顯示器，因此給個輸出文件夾；
當(dāng)前工程下，新建models文件夾用來放測試模型，當(dāng)然，模型自己在model zoo鏈接中去下載；
其他參數(shù)：
在攝像頭測試
用–webcam替代–input
視頻文件測試
用–video-input替代–input
存儲結(jié)果
給–output參數(shù)就行
https://blog.csdn.net/enwuone/article/details/104983976
python demo/demo.py --config-file
configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml --input 001.jpg
--output results --opts MODEL.WEIGHTS
detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl
參數(shù)解釋
demo/demo.py：demo文件
–config-file：選擇配置文件
–output：輸出位置（如果想直接查看，刪除這個參數(shù)即可）
MODEL.WEIGHTS：預(yù)先訓(xùn)練好的模型
pip install opencv-python --user? // no module named cv2
4) others
RuntimeError: Not compiled with GPU support
//不生效，可以參考begin
https://www.cnblogs.com/marsggbo/p/11916859.html
官方提供的檢驗(yàn)代碼查看CUDA路徑：
python -c 'import torch; from torch.utils.cpp_extension
import CUDA_HOME; print(torch.cuda.is_available(), CUDA_HOME)'
vim ~/.bashrc
export CUDA_HOME=/usr/local/cuda
source ~/.bashrc
Docker Runtime Error: Not Compiled with GPU support
https://github.com/facebookresearch/maskrcnn-benchmark/issues/167
https://blog.csdn.net/u011420347/article/details/85111815
https://ask.csdn.net/questions/769137
print(t.version.cuda)
print(t.cuda.device_count())
import torch as t
tensor=t.Tensor(3,4)
tensor.cuda(0)
google搜索，參考
https://github.com/facebookresearch/detectron2/issues/62
https://github.com/facebookresearch/detectron2/issues/267
//end
