forked from huggingface/pytorch-image-models
-
Notifications
You must be signed in to change notification settings - Fork 0
merge original #2
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
Merged
Merged
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
…xperimenting...
Initial implementation of blur layer. currently tests as correct against Downsample of original github
clean up code for PR
1. add ResNet argument blur='' 2. implement blur for maxpool and strided convs in downsampling blocks
…and tweaks to go...
Experimental feature extraction interface seems to be changed a little bit with the most up to date version apparently found in EfficientNet class. Here these changes are added to MobileNetV3 class to make it support it and work again, too.
Merge changes in feature extraction interface to MobileNetV3
TResNet models
* allow use of global pool arg, test-time-pooling * clean checkpoints to just contain state dict, add 448 res checkpoints * support DataParallel via lazy filter creation for JIT Downsample * some minor formatting (mostly alignment) preferences
…ce any perf difference
…orch-image-models into yoniaflalo-adding_ECA_resnet
…rmatting alignment tweaks.
fix typo in eca
…into VRandme-blur
…Downsample arg order to BlurPool2d for interop
…with AMP + channels_last layout. See pytorch/pytorch#43992
…, normal one is now 'fast'
… train/validate to avoid channels_last issue with AdaptiveAvgPool
Native Torch AMP and channels_last support for train.py and validate.py
Utils refactor, more cutmix modes / change mode arg
…n PyTorch. More sotabench fiddling.
…lename extraction consistency
… impl tweak and dedupe se args.
…oling is not available
Bug fix: test_time_pool would be set to a non-False value
…aler interfaces to support unscaled grad clipping. Bump ver to 0.2.2 for pending release.
…g, add gradient clipping support.
…mizer factory. Fix #247
…th older torch ver for released models
Vision Transformer
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.
No description provided.