Skip to content
This repository has been archived by the owner on Jul 2, 2023. It is now read-only.

Issues: wkentaro/pytorch-fcn

The learning rate is too small
#54 by youngfly11 was closed Sep 24, 2017
Closed 5
About VGG16 pretrained model
#52 by zijundeng was closed Sep 23, 2017
Closed 6
Why do we need padding=100 for a filter of size 3?
#40 by deartonym was closed Aug 2, 2017
Closed 5
Clear current search query, filters, and sorts
21 Open 121 Closed
21 Open 121 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

IncompatibleKeys(missing_keys=[], unexpected_keys=[]) for FCN32 help wanted
#131 opened Aug 6, 2019 by AlexTS1980 updated Aug 28, 2019
1
CPU memory usage is high question
#139 opened Oct 10, 2019 by LiheYoung updated Oct 12, 2019
1
weight returned by get_upsampling_weight?
#142 opened Oct 29, 2019 by Lucksong updated Oct 29, 2019
TypeError: expected np.ndarray (got numpy.ndarray) help wanted
#124 opened Jun 19, 2019 by Iamyourbaba updated Nov 28, 2019
3
Why the parameter of bias is set False to nn.ConvTranspose2d() in fcn8s.py?
#146 opened Jan 17, 2020 by songyuc updated Jan 17, 2020
"pip install torchfcn "have error!!--------error: can't copy 'torchfcn/ext/fcn.berkeleyvision.org': doesn't exist or not a regular file more-information-needed
#127 opened Jul 12, 2019 by XGuider updated Feb 15, 2020
5
About download datasets
#143 opened Nov 1, 2019 by BangguWu updated Feb 18, 2020
1
The begining index to crop output images in fcn32s.py
#147 opened Feb 9, 2020 by gniknoil updated Feb 23, 2020
1
ValueError: Unexpected module: FCN8sAtOnce question
#123 opened Jun 11, 2019 by chentao2016 updated Mar 26, 2020
@wkentaro
3
I use vgg16 pretrained model to train ,but the result of fcn32s is zero, can you help me?
#150 opened Mar 19, 2020 by hylovezhang updated Mar 26, 2020
feature map size after upsample is 2h or 2(h+1)?
#141 opened Oct 12, 2019 by Lucksong updated Mar 26, 2020
3
requests.exceptions.ConnectionError
#154 opened Jun 30, 2020 by Wenenen updated Nov 28, 2020
5
Why the padding of first conv layer in FCN32s is 100?
#157 opened Nov 29, 2020 by msy1412 updated Jan 5, 2021
3
Load FCN8 weights
#145 opened Dec 4, 2019 by luistelmocosta updated May 23, 2021
1
Pretrained model 404
#160 opened May 30, 2021 by BlackDriver updated Jul 6, 2021
4
I have the same problem, all output results are zeros. Anyone can help ?
#144 opened Nov 21, 2019 by prfans updated Nov 6, 2021
5
why all my output results of the fcn32 is ZERO help wanted question
#113 opened Mar 28, 2019 by daiyp3360xxxxxisxxxxxxmine updated Nov 6, 2021
16
这是怎么处理的？
#165 opened Nov 24, 2021 by Shajiu updated Nov 24, 2021
What h[:, :, 31:31 + x.size()[2], 31:31 + x.size()[3]] mean?
#161 opened Jun 10, 2021 by lyw615 updated Oct 9, 2022
6
Gradient explosion occurs after modifying the weight initialization method
#167 opened Oct 22, 2022 by eadstry updated Oct 22, 2022
How to change batch_size？
#168 opened Apr 29, 2023 by Lukashsx updated Apr 29, 2023
1
ProTip! Add no:assignee to see everything that’s not assigned.