R-C3D.pytorch

R-C3D.pytorch copied to clipboard

RuntimeError: dimension out of range (expected to be in range of [-1, 0], but got 1)

3

R-C3D.pytorch/lib/roi_data_layer/roibatchLoader.py", line 36, in __getitem__ gt_windows_padding = gt_windows.new(self.max_num_box, gt_windows.size(1)).zero_() RuntimeError: dimension out of range (expected to be in range of [-1, 0], but got 1) Hi, did you meet the...

JackSyu

An error occured when I trained the model on my own dataset.

3

When I recurrent the R-C3D model to achieve the action recognization task on my own dataset, I had the same problem. [session 1][epoch 1][iter 1/ 30] loss: 2.5127, lr: 1.00e-04...

Sagiri18

THUMOS14数据准备

1

请问THUMOS原始数据是怎么准备的？detclasslist.txt在哪里？

zhujiwei1234

I used the benchmark models you provided and tested them directly without changing any hyper-parameters. However, I got only 25.5 [email protected] results on ActivityNet with the C3D backbone, which is...

tangyip

Hi, @sunnyxiaohu ! R-C3D achieves a very good performance on the Thumos14 dataset. I can reach 0.4175 @ IoU 0.5 using your implementation. However, it does not perform as well...

coolbay

Hi, Thanks for your work. I am a little bit curious about the output results. In your report mAP(IoU thresh=0.5) of RC3D is 28.9 on THUMOS14, yet that of C3D...

KevinQian97

The Pretrained Models are not available except Baiduyun

blueskyM01


yukeqi12345

train_net.py 问题

9


dangao250

Why your model has such impressive performance?

4

I downloaded your trained model (C3D on THMOUS14) and tested, I got mAP 37 for threshold 0.5. It is higher than SOTA. But I noticed that the Len(dataloader) is 8355,...

mlii0117