semchan

Is that possible to release the detection demo?

4

Greeting! since there is only evaluation for proposals, do you plan to release the detection code? thanks.

AUC result

2

wonderful work! I saw the result in your code is about 68%, but in http://activity-net.org/challenges/2019/evaluation.html, the result of your method got about 73%, may I know what is the gap?...

hi, how to understand the code " rgb_marched = segment_coo"? thanks

2

Hi, thanks for your great work. May I know how to understand the below code? thanks a lot. ``` rgb_marched = segment_coo( src=(weights.unsqueeze(-1) * rgb), index=ray_id, out=torch.zeros([N, 3]), reduce='sum') ```...

the link of the paper is wrong, please check.

1

"This repository contains a pytorch lightning implementation for the ICCV 2021 paper: MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo. "

Running VIBE on each tracklet... 100%|███████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:05

hi, when I use gen_trimap.sh, but got the error:, may I know where is the train.txt? thanks [Errno 2] No such file or directory: './train.txt'

Wrong JPEG library version: library is 80, caller expects 62

1

hi, when I run below code, there pop out the error of "Wrong JPEG library version: library is 80, caller expects 62", do you know why? and how to fix...

Loss: nan

4

您好！我发现多轮训练后会出现 Loss: nan　的情况，仔细看代码，有一点点不是特别明白想请教您：如下代码中计算loss时为何需要先exp()再求log呢？这里如果score[0][x][y]如果为０，就会出现loss等于nan的情况．另外，这里求loss与论文中似乎有点差别呢？期待您的解答． # check if indexed correctly loss = [] for i in range(len(all_matches[0])): x = all_matches[0][i][0] y = all_matches[0][i][1] loss.append(-torch.log( scores[0][x][y].exp() )) # check batch size ==...

hi, error: identifier "nullptr" is undefined

6

hi, I follow your suggestion to build this firstly, but I got the below errors, would you please help me? maybe the gcc version or something is not correct. thanks...