Update attention / self-attn based models from a series of experiments #821
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Collaborator
rwightman commented Aug 20, 2021
rwightman commented - remove dud attention, involution + my swin attention adaptation don't seem worth keeping
- add or update several new 26/50 layer ResNe(X)t variants that were used in experiments
- remove models associated with dead-end or uninteresting experiment results
- weights coming soon...
* remove dud attention, involution + my swin attention adaptation don't seem worth keeping * add or update several new 26/50 layer ResNe(X)t variants that were used in experiments * remove models associated with dead-end or uninteresting experiment results * weights coming soon...
…p / fixes for byoanet. Rename resnet26ts to tfs to distinguish (extra fc).
* add polynomial decay 'poly' * cleanup cycle specific args for cosine, poly, and tanh sched, t_mul -> cycle_mul, decay -> cycle_decay, default cycle_limit to 1 in each opt * add k-decay for cosine and poly sched as per https://arxiv.org/abs/2004.05909 * change default tanh ub/lb to push inflection to later epochs
…g as an alternate to CE w/ smoothing. For training experiments.
…current (distributed) training experiments.
…pdates, repeat augment, and bce loss
… with at least one halo in stage 2,3,4
…ll trying to improve reliability of sgd test.
…f, now figuring out why they were so low...
…d SE-HaloNet33-TS weights.
guoriyue pushed a commit to guoriyue/pytorch-image-models that referenced this pull request May 24, 2024
Update attention / self-attn based models from a series of experiments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Add this suggestion to a batch that can be applied as a single commit. This suggestion is invalid because no changes were made to the code. Suggestions cannot be applied while the pull request is closed. Suggestions cannot be applied while viewing a subset of changes. Only one suggestion per line can be applied in a batch. Add this suggestion to a batch that can be applied as a single commit. Applying suggestions on deleted lines is not supported. You must change the existing code in this line in order to create a valid suggestion. Outdated suggestions cannot be applied. This suggestion has been applied or marked resolved. Suggestions cannot be applied from pending reviews. Suggestions cannot be applied on multi-line comments. Suggestions cannot be applied while the pull request is queued to merge. Suggestion cannot be applied right now. Please check back later.