mathsshen / dasiamrpnwithofflinetraining Goto Github PK

Hi, MathsXDC:
Thank you for your great work! I've just read your implementation, and I'm having trouble finding the implementation of distractor-aware training part in your code. I briefly summarized my questions as below:

1. How do you sample negative pairs in your code?
2. Did you test your performance on the vot benchmark?

It would be great if you could enlighten me on above questions. Thank you very much!

Sorry to interrupt u,and i really thank u for ur work. when i run train.py, i got some questions ,'xxxx' object has no attribute 'to' .Is that caused by the version of pytorch.The version of torch is 0.3.1?

Thank you very much for your work!
But when I run the model with incremental learning using SiamRPNBig.model provided by the author of the paper, it seems not work. I edit the net.py file to use the trained model without changing the structure of the network. Would you please give me some suggestions on my problem.

File "train.py", line 260, in
mask = torch.from_numpy(mask).to(DEVICE)
RuntimeError: CUDA error: an illegal memory access was encountered

Can you share me your way of contact? I really need your hlep about this project. Thanks!

I use the same pretrained model SiamRPNBIG.model in https://github.com/foolwood/DaSiamRPN to run this repo. (after motified some code). However, it's extremely slow(can't even achieve 1 fps). I run foolwood version with these parameters very normally.

when running the code, the cls_loss will be nan. I think it is because of the 'mask' in train.py can be zero. But I am not sure. And another question is that when running the code, there will be a error "cuda runtime error: an illegal memory access was encountered". hoping to hear from you soon. thank you very much

Traceback (most recent call last):
File "train.py", line 245, in
reg_loss = reg_loss_fn(reg_output[i], torch.from_numpy(rpn_bbox_targets).to(DEVICE), torch.from_numpy(rpn_bbox_inside_weights).to(DEVICE), torch.from_numpy(rpn_bbox_outside_weights).to(DEVICE))
File "train.py", line 62, in smooth_l1_loss
loss_box = loss_box.view(-1).sum(0) / N
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

how to solve this problem? I am not familiar with pytorch, I am not sure whether my revision to this code was correct. I changed as follows:

• loss_box = loss_box.view(-1).sum(0) / N
  +loss_box = torch.reshape(loss_box, (-1,)).sum(0) / N

but the loss become nan like
Epoch0 Iter1 --- total_loss: nan, cls_loss: nan, reg_loss: 0.1331
17%|██████████████████████████████ | 2/12 [00:03<00:22, 2.22s/it]Epoch0 Iter2 --- total_loss: nan, cls_loss: nan, reg_loss: 0.6188
25%|█████████████████████████████████████████████ | 3/12 [00:05<00:17, 1.98s/it]Epoch0 Iter3 --- total_loss: nan, cls_loss: nan, reg_loss: 1.5328
33%|████████████████████████████████████████████████████████████ | 4/12 [00:06<00:14, 1.81s/it]Epoch0 Iter4 --- total_loss: nan, cls_loss: nan, reg_loss: 2.0786

I got overwhelmed!!

Hey, great work.

Can you share the pre-trained weights. Also did you had a chance test your updated code on the original SiamRPNBIG.model, SiamRPNVOT.model, SiamRPNOTB.model?

Hello, thank u for ur great work!!!! Thanks a lot.
After modifying some code, the train.py can run successfully.
But the loss is very strange, as follow:
0%| | 0/8 [00:00<?, ?it/s]Epoch0 Iter0 --- total_loss: nan, cls_loss: nan, reg_loss: 0.6299
12%|█▎ | 1/8 [00:02<00:14, 2.01s/it]Epoch0 Iter1 --- total_loss: nan, cls_loss: nan, reg_loss: 1.7844
25%|██▌ | 2/8 [00:03<00:09, 1.61s/it]Epoch0 Iter2 --- total_loss: nan, cls_loss: nan, reg_loss: 34.9781
38%|███▊ | 3/8 [00:04<00:07, 1.48s/it]Epoch0 Iter3 --- total_loss: nan, cls_loss: nan, reg_loss: 238.0343
50%|█████ | 4/8 [00:05<00:05, 1.41s/it]Epoch0 Iter4 --- total_loss: nan, cls_loss: nan, reg_loss: 236.5256
62%|██████▎ | 5/8 [00:06<00:04, 1.37s/it]Epoch0 Iter5 --- total_loss: nan, cls_loss: nan, reg_loss: 70.5485
75%|███████▌ | 6/8 [00:08<00:02, 1.35s/it]Epoch0 Iter6 --- total_loss: nan, cls_loss: nan, reg_loss: 113.4333
88%|████████▊ | 7/8 [00:09<00:01, 1.33s/it]Epoch0 Iter7 --- total_loss: nan, cls_loss: nan, reg_loss: 56.8303
100%|██████████| 8/8 [00:10<00:00, 1.25s/it]
Saving model...

Have u met it before? Thanks.

could you please share a demo of sample? I'm a little confused of its format. Thank you.

First, I'd like to thank you for your work!
I try to run 'train.py' with pytorch=0.3.1,but got lots of errors. It seems that your training code was implemented by pytorch0.4.0? For ex. 'torch.device()'.