vedatad

vedatad copied to clipboard

Question about test

3

Hi, I ran the code of test, and the results are shown as blow.  I wonder whether the repo supports evaluation of mAP of iou@[03:0.7], as reported in the...

wjn922

question about test result

3

 Hi, I ran the code of test, and the results are shown as up. The result I got is much lower than the result of the paper, what is...

yilonghe

- We added some code to parse the MultiTHUMOS dataset - Added the config files for MultiTHUMOS training - Added code to load weights from intermediate epochs - Also fixed...

gauthsvenkat

question about .cpp

2

在dcn/deform_conv.py文件中导入了.cpp文件， from . import deform_conv_ext，deform_conv_ext.cpp等文件您是怎样编译的呢？我没找到编译命令，烦请指点。

yilonghe

Thank you for you excellent work! I have a question about the fps. The fps is 25 when you extract frames, but the fps of the video is 30, and...

ArthurUnic

How is data needed to be prepared for using `InferEngine` If my inference was something like ```python def read_video(video): '''Read video prepare video_metas''' pass def prepare(cfg, checkpoint): engine = build_engine(cfg.infer_engine)...

connor-john

Labels: background as 1, foreground as 0?

1

Hi guys, thanks for your work and sharing the code. I have a question about the labels input to calculate the loss. So I understand it as if we have...

yt2639

how can I save the parament of my own net while Training?

1

Umaruchain

Umaruchain

Goubeast