Skip to content

Issues: pppLang/SKNet

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

19 Open 3 Closed
19 Open 3 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [8, 64, 32, 32]], which is output 0 of ReluBackward0, is at version 1; expected version 0 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later.
#23 opened May 12, 2022 by Jin-Xi
2
what's the env to run "main" code?
#22 opened Jan 8, 2022 by fangzhouAlonso
error: attention_vectors = torch.cat([attention_vectors, vector], dim=1)
#21 opened Dec 14, 2020 by dangxusheng
The Global Average Pooling
#20 opened Oct 20, 2020 by jianjiandandande
2
RuntimeError: size mismatch, m1: [12288 x 3], m2: [1024 x 196]
#19 opened Aug 10, 2020 by Lin-plax
Why no 'dilation'?
#18 opened Jul 7, 2020 by decoli
1
Why is the SKConv very different from the figure shown in the README?
#17 opened Jul 1, 2020 by LiDaiY
kernel size of first conv
#16 opened Apr 17, 2020 by doitslow
RuntimeError: Given input size: (1024x4x4). Calculated output size: (1024x0x0). Output size is too small
#15 opened Feb 28, 2020 by caisong1995
1
cuDNN error: CUDNN_STATUS_NOT_SUPPORTED
#14 opened Feb 14, 2020 by LJXLJXLJX
您好，问一下关于sknet.py的问题
#13 opened Jan 3, 2020 by Xuecheng-anhui
3
RuntimeError
#12 opened Nov 25, 2019 by liu-ca
the param "WH" is not used in the SKConv and SKUint module
#9 opened Aug 30, 2019 by xiaohuihuichao
About "attention_vectors = torch.cat([attention_vectors, vector], dim=1)"
#8 opened Jun 13, 2019 by Chao86
2
Any plan about providing pretrained models?
#7 opened May 14, 2019 by nemonameless
when batchsize=1，I got this error
#6 opened Apr 20, 2019 by yangdb
1
skc have error
#5 opened Apr 15, 2019 by GGjerry01
implementation result
#4 opened Apr 15, 2019 by zliangak
1
RuntimeError: Given input size: (128x16x16)
#2 opened Mar 31, 2019 by zyyhl
1
ProTip! Add no:assignee to see everything that’s not assigned.