fast-reid复现（windows-cpu）
0.环境
windows(cpu)
#torch==1.2.0+cpu -f https://download.pytorch.org/whl/torch_stable.html
#torchvision==0.4.0+cpu -f https://download.pytorch.org/whl/torch_stable.html
Cython
yacs
tensorboard
future
termcolor
sklearn
tqdm
opencv-python==4.1.0.25
matplotlib
torch与torchvision的安装：
pip install torch==1.2.0+cpu torchvision==0.4.0+cpu -f https://download.pytorch.org/whl/torch_stable.html其他的都使用安装：
pip --default-time=500 install -i https://pypi.tuna.tsinghua.edu.cn/simple -r requirements.txt1.下载
参考：https://blog.csdn.net/qq_35975447/article/details/106664593
2.训练
修改1：
fast-reid-master\fastreid\data\common.py
prefix = file_path.split('/')[1]
to:
prefix = file_path.split('\\')[1]
或者一劳永逸的办法：
import platform
sysstr = platform.system()
if (sysstr == "Windows"):
prefix = file_path.split('\\')[1]
elif (sysstr == "Linux"):
prefix = file_path.split('/')[1]
修改2（注释几处地方）：
./tools/train_net.py
.\fastreid\engine\defaults.py
.\fastreid\evaluation\rank.py
或者直接不使用cython的修改（issue74）：
训练：
python ./tools/train_net.py --config-file="绝对路径\configs\Market1501\AGW_R50.yml"
eg:
python ./tools/train_net.py --config-file="E:\work\fast-reid-master\configs\Market1501\AGW_R50.yml"会因为使用的CPU报一些警告（且训练会比较慢）：
WARNING:root:This caffe2 python run does not have GPU support. Will run in CPU only mode.
75次迭代，花了2-3小时~.~还跑的基本款(resnet50)
?[32m[06/12 17:14:23 fastreid.engine.hooks]: ?[0mOverall training speed: 75 iterations in 2:49:15 (135.4069 s / it)
3.可视化(CPU近3小时多)
可以将服务器上或者GPU设备上训练的logs里面的文件复制到windows下，然后进行可视化工作。
修改demo/visualize_result.py
注释\fast-reid-master\fastreid\utils\visualizer.py line69 :
python ./demo/visualize_result.py --config-file "E:\pythonwork\fast-reid-master\configs\Market1501\AGW_R50.yml" --vis-label --dataset-name "Market1501" --output "logs/market1501/agw_R50/agw_market1501_vis" --opts MODEL.WEIGHTS "./logs/market1501/agw_R50/model_final.pth"
