search

NVlabs / DG-Net

:couple: Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral) :couple:
https://www.zdzheng.xyz/publication/Joint-di2019
Other
1.28k stars 228 forks source link

IndexError:Dimension out of range(excepted to be in range of [-1,0],but got 1) #75

Open aiqiangbrave opened 2 years ago

aiqiangbrave commented 2 years ago

Hello,can you help me ?thank you! When I use Market data set ,report an error:

problem: /home/waq/anaconda3/envs/re_person/bin/python /home/waq/Downloads/ai/re_person/code/DG-Net/DG-Net-master/test_2label.py -------test----------- /home/waq/Downloads/ai/re_person/code/DG-Net/DG-Net-master/test_2label.py:182: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details. config = yaml.load(stream) Traceback (most recent call last): File "/home/waq/Downloads/ai/re_person/code/DG-Net/DG-Net-master/test_2label.py", line 204, in gallery_feature = extract_feature(model,dataloaders['gallery']) File "/home/waq/Downloads/ai/re_person/code/DG-Net/DG-Net-master/test_2label.py", line 131, in extract_feature x[0] = norm(x[0]) File "/home/waq/Downloads/ai/re_person/code/DG-Net/DG-Net-master/test_2label.py", line 109, in norm fnorm = torch.norm(f, p=2, dim=1, keepdim=True) File "/home/waq/anaconda3/envs/re_person/lib/python3.6/site-packages/torch/functional.py", line 1337, in norm return _VF.norm(input, p, _dim, keepdim=keepdim) # type: ignore IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)

Process finished with exit code 1

Thank you！

nikky4D commented 2 years ago

Check the size of the matrix/vector in x[0], if it has a 1 in the batch dimension, after squeeze in norm() function, this reduces to a vector which is problematic for the norm

layumi commented 2 years ago

Yes @aiqiangbrave

It is due to the batch size = 1

You could use 

if len(x.shape) ==2:
    x = x.unsqueeze(0)

Something like that.

aiqiangbrave commented 2 years ago

okok,thank you for your reply.

---- 回复的原邮件 ---- | 发件人 | Zhedong @.> | | 日期 | 2022年04月20日 22:57 | | 收件人 | @.> | | 抄送至 | @.**@.> | | 主题 | Re: [NVlabs/DG-Net] IndexError:Dimension out of range(excepted to be in range of [-1,0],but got 1) (Issue #75) |

Yes @aiqiangbrave

It is due to the batch size = 1

You could use

x = x.unsqueeze(0)

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.***>

aiqiangbrave commented 2 years ago

Check the size of the matrix/vector in x[0], if it has a 1 in the batch dimension, after squeeze in norm() function, this reduces to a vector which is problematic for the norm

okok,thank you!