yyh

For example, I type： python yolo_video.py [1.mp4] or python yolo_video.py [C:\Users\keras-yolo3\1.mp4] response is : model_data/yolo.h5 model, anchors, and classes loaded. warning: Error opening file (/build/opencv/modules/videoio/src/cap_ffmpeg_impl.hpp:808) warning: [1.mp4] (/build/opencv/modules/videoio/src/cap_ffmpeg_impl.hpp:809) Traceback (most...

Thanks a lot! MartinWeniger You really help me a lot!

I made a small demo by using this library and a street dance video. See here: https://www.youtube.com/watch?v=XyInRQF3mq4

haha, thanks for your help with the initial read in video problem, can't make it without your help

I have the same problem

It is working now. Thanks a lot!

我也遇到了同样的问题，修改成’resnet_v1/SpatialSqueeze:0‘ 就不会报错了，但似乎预测有问题，我还在测试，不知道是不是名字不对

每次max pooling减半

After run demo: ` import sys import torch import tensorwatch as tw import torchvision.models alexnet_model = torchvision.models.alexnet() tw.draw_model(alexnet_model, [1, 3, 224, 224]) ` [MAdd]: AdaptiveAvgPool2d is not supported! [Flops]: AdaptiveAvgPool2d...