vision4robotics / udat Goto Github PK

Hi, I try to train UDAT with 4 2080 Ti. However, dp mode causes uneven distribution of GPU memory. For example, only the main GPU occupies 11G, while the remaining three occupy only 6G on average. I change it to DDP mode but it doesn't work. Would you have any ideas?

Besides, I find several bugs.

1. in the train.py, when calculating the summation of discriminator output, the numpy function cannot operate on tensors with grad.
   i.e., train.py line 257-258, 285-286, 297-298

D_out_z = np.sum([Disc(F.softmax(_zf_up_t, dim=1)) for _zf_up_t in zf_up_t])/3.0
D_out_x = np.sum([Disc(F.softmax(_xf_up_t, dim=1)) for _xf_up_t in xf_up_t])/3.0

I think it should be

D_out_z = torch.stack([Disc(F.softmax(_zf_up_t, dim=1)) for _zf_up_t in zf_up_t]).sum(0) / 3.
D_out_x = torch.stack([Disc(F.softmax(_xf_up_t, dim=1)) for _xf_up_t in xf_up_t]).sum(0) / 3.

2. in the eval.py, the line 67 elif 'NAT' in args.dataset: should be elif 'NAT' == args.dataset:. Otherwise, the results of NAT_L would also go into this branch.

Hi,I have some questions about this paper.
Figure 4 in the paper reports the t-SNE results of the features before and after the Bridging layer. I want to know whether the t-SNE input here is the feature of the domain transformer discriminator or the original feature directly output by the Bridging layer. If so, does the feature output by the Feature extractor before the Bridging layer need to train an additional domain discriminator.
Thank you!

Hello, I am interesting in the training strategy of your paper. Why you choose an alternatively training strategy to optimize G and D? It seems to be straightforward to train end-to-end, since you use a RevGrad layer.

I wonder how you implement Grad-CAM in RPN cls and loc head, can you provide help?
Thank you.

作者，您好！
我想请教一下，论文中图9如何绘制

Hi. I have two questions:

1. It seems that there is no val dataset in NAT, so do you directly use the model saved in the last epoch to test?
2. Since the train set of NAT does not have labels and the two baselines(SiamCAR & SiamBAN) are supervised methods, I wonder whether the results of two baselines used to compare with UDAT are only trained on GOT-10K and VID.

Hello, I'm very interested in your research. Because the datasets are too large, it is not easy to run through the code. I want to know the size of the feature extractor when it is passed into the transformer bridging layer. Does the feature size change after feature alignment？

您好，感谢你的工作成果。请问训练出来的有两个模型，checkpoint.pth和d_checkpoint.pth，请问测试的时候是用哪个模型？d_checkpoint的作用是什么？谢谢!

The ‘0175bike1_3.npy’ generated by gen_seq_bboxes.py is all nan

尝试复现您的结果，但未能得到满意的效果，不知是否是复现步骤的问题，如果可以的话，请提供详细的复现步骤。

Dear author, thank you very much for your work.
I wonder if the t-SNE code used in Figure 4 will be made public?
This visualization method is very interesting!
Thanks in advance!