Ming Li

Is the number of frames used for training is differ from the number of frames used for testing?

1

Thanks for your contribution! I want to know the number in the table below is used for training or used for testing or both them? In other words, Is the...

I have ran the code many times(about 100 times), same environment with requirements.txt, even changed 3 different machines, but the best result I could get is about to 40, much...

Different hyperparameters between paper and code

1

For iNaturalist: learning rate is decay at 60th and 80th epoch by 0.1 (in paper), but lr is decay at 120 and 160 in your [code](https://github.com/Megvii-Nanjing/BBN/blob/7992e908842f5934f0d1ee3f430d796621e81975/configs/iNaturalist2018.yaml#L47) could you please check...

Hi, could you release the pretrained models for CIFAR-10 and CIFAR-100? I cannot reproduce the results reported in your paper, which means I cannot analyze some informations with BBN

CUDA Error when pytorch distribution training...

6

Hi, thanks for your contribution, when I using distribution training, there is always RuntimeError: `RuntimeError: CUDA error: invalid device function`, here is my test code: ``` import torch from spatial_correlation_sampler...

How to plot the figures?

2

Hi @KaiyangZhou, Could you please kindly provide the code used for the visualization of the feature learning process?

Hi, could you please tell me that is still 25 fps used when extracting features of ActivityNet?

Have you tried 90 epochs training with mixup on ImageNet or iNaturalist ?

2

Hi @zs-zhong , Have you tried 90 epochs training with mixup on ImageNet or iNaturalist ? I have made some improvements based on your work, but due to the lack...

Thanks for your contribution. In your paper there are 32 frames when evaluating Kinetics-400, both in R-50 and R-101. Could you please tell me did you also use 32 frames...

AssertionError: Invalid boxes

1

Hi @SuperHenry2333 @SlongLiu @FengLi-ust Update: some bboxes after data augmentation are `nan`:  --- I tried to reproduce the Objects365 pre-training with a large resolution, however, this error always occurs....