-
Notifications
You must be signed in to change notification settings - Fork 1.1k
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.
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
[Feature] Support Wide ResNet #715
Conversation
Thank you for your contribution to We notice there are checkpoints for wide resnet. Could you use the script(as below) to convert torchvison ckpt into mmcls ckpt and make sure that the inference accuracy in Imagnet-1k are the same? after convert and prepare the magnet-1k val dataset. run
torchvison_to_mmcls.py
|
I've confirmed that the accuracy is almost same after model conversion.
I would like to ask you about CLA. |
Actually, the accuracy should be the same. So there is something different with setting in torchvision. Maybe it causes by Resize backend, You can try:
Did you mean that you have pushed your commits before config your email address, which caused the username unable to be tracked? Maybe you need to use |
I confirmed the accuracy is the same as torchvision by modifying resize backend.
Yes, I modified commit message. |
Great! Please update the configs. Later, I will add some docs about wide-ResNet. Could I just commit to your branch directly? |
Sure! please. |
Codecov Report
@@ Coverage Diff @@
## dev #715 +/- ##
=======================================
Coverage 84.94% 84.94%
=======================================
Files 121 121
Lines 7548 7548
Branches 1303 1303
=======================================
Hits 6412 6412
Misses 944 944
Partials 192 192
Flags with carried forward coverage won't be shown. Click here to find out more. Continue to review full report at Codecov.
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
No support for 3 stage WRN? like WRN 16 to WRN 40? |
@Davidgzx Can you attach the code and weights link? |
@Davidgzx In the official repo, the wrn16 or the wrn40 are trained by using cifra10 and cifra100. I think the ImagNet-1k dataset is more general. |
* Add configs of Wide ResNet * updated config * add docs and metafile * update configs * remove extra import * Update metafile and readme Co-authored-by: Ezra-Yu <1105212286@qq.com> Co-authored-by: mzr1996 <mzr1996@163.com>
Hi @yasu0001!First of all, we want to express our gratitude for your significant PR in the MMClassification project. Your contribution is highly appreciated, and we are grateful for your efforts in helping improve this open-source project during your personal time. We believe that many developers will benefit from your PR. We would also like to invite you to join our Special Interest Group (SIG) private channel on Discord, where you can share your experiences, ideas, and build connections with like-minded peers. To join the SIG channel, simply message moderator— OpenMMLab on Discord or briefly share your open-source contributions in the #introductions channel and we will assist you. Look forward to seeing you there! Join us :https://discord.gg/UjgXkPWNqA If you have WeChat account,welcome to join our community on WeChat. You can add our assistant :openmmlabwx. Please add "mmsig + Github ID" as a remark when adding friends:) |
Motivation
Based on #678
Modification
Add two wide resnet config files for ImageNet.