Xinglong Sun

Is there anyone able to achieve close to paper-reported accuracy using this repo code? Thanks!

Training Log

4

Thanks for the nice work! Is there any chance that the training loss log can be released? That can greatly help my debugging process.

Is there any other hidden settings or tricks for training

4

I followed your paper and tf code and reimplemented your model in PyTorch and trained from scratch but can only get 77.9 map for VOC2007

Why the zeroed channels still receive gradients?

1

Theoretically speaking, when you prune the channels according to the output dimension, you shouldn't get any gradient for the corresponding weights during your backward pass. How do you solve this...

visibility

2

thanks for the great work! the conf score in the dataset could be as a visibility score of the object right?

Cameras Missing

1

In some of the segments, I observe that not all cameras data exist, for example: segment-12681651284932598380_3585_280_3605_280_with_camera_labels Is this normal?