Add SWAG Vision Transformer Weight#5714
Conversation
💊 CI failures summary and remediationsAs of commit c36a3ec (more details on the Dr. CI page): ✅ None of the CI failures appear to be your fault 💚
🚧 2 ongoing upstream failures:These were probably caused by upstream breakages that are not fixed yet.
This comment was automatically generated by Dr. CI (expand for details).Please report bugs/suggestions to the (internal) Dr. CI Users group. |
datumbox
left a comment
There was a problem hiding this comment.
Thanks @YosuaMichael. I've added a couple of comments but overall I like your approach:
…dle case where number of param differ from default due to different image size input
datumbox
left a comment
There was a problem hiding this comment.
Looking good. Could you provide also the commands that you used to verify the model along with their output? Something similar to #5450 (comment) (note that the commands will be slightly different because the Multi-weight support API is out of prototype).
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
|
@datumbox here is the command I used for testing the And here for |
datumbox
left a comment
There was a problem hiding this comment.
Thanks a lot of the changes @YosuaMichael, everything looks good to me.
@mannatsingh Could you have also a look to let us know if all look good to you?
mannatsingh
left a comment
There was a problem hiding this comment.
Everything looks perfect, thanks @YosuaMichael !
|
The failures are unrelated. cc @pmeier @YosuaMichael you are good to merge. |
Summary: * Add vit_b_16_swag * Better handling idiom for image_size, edit test_extended_model to handle case where number of param differ from default due to different image size input * Update the accuracy to the experiment result on torchvision model * Fix typo missing underscore * raise exception instead of torch._assert, add back publication year (accidentally deleted) * Add license information on meta and readme * Improve wording and fix typo for pretrained model license in readme * Add vit_l_16 weight * Update README.rst * Update the accuracy meta on vit_l_16_swag model to result from our experiment Reviewed By: NicolasHug Differential Revision: D35393156 fbshipit-source-id: d8e38f783c3c881cf8a8ce21d05a33671818be53 Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com> Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
subtask of #5708
Adding weight of ViT_B_16 and ViT_L_16 model from https://github.com/facebookresearch/SWAG