search

ColumbiaDVMM / CDC

CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos
68 stars 18 forks source link

2 Bugs need to fixed #15

Closed ChenyangLiu closed 6 years ago

ChenyangLiu commented 6 years ago

Thank you for share your code, it's a really good work. But there are some problems in your project.

  1. In frame_wise_softmax_loss_layer.cpp:86, you want to take into account ambiguous frame, that works fine on the dataset with ambiguous. But if I want to use this project on my data, that will be confused. I think it's better to ignore ambiguous in preprocess, not in caffe layer.

  2. During my training, I found that some -nan appears randomly, even I set my lr=1e-9. And I find that there is a typo in voxel_wise_softmax_layer.cpp:66. It should be max(scaledata[scale.offset(i,0,l,h,w)], since the bottom[0] and the scale_ have different shape. It may subtract a huge number in the next step, and -nan appears.

zhengshou commented 6 years ago

Thank you so much for reporting the concerns and issues. Will look into it soon in the following days. Thanks.