Ross Wightman
|
70ae7f0cc2
|
Merge pull request #250 from rwightman/vision_transformer
Vision Transformer
|
4 years ago |
|
Ross Wightman
|
be53107e8a
|
Update README, ensure vit excluded from all tests (not ready)
|
4 years ago |
|
Ross Wightman
|
f31933cb37
|
Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.
|
4 years ago |
|
Ross Wightman
|
9305313291
|
Default to old checkpoint format for now, still want compatibility with older torch ver for released models
|
4 years ago |
|
Ross Wightman
|
a4d8fea61e
|
Add model based wd skip support. Improve cross version compat of optimizer factory. Fix #247
|
4 years ago |
|
Ross Wightman
|
80078c47bb
|
Add Adafactor and Adahessian optimizers, cleanup optimizer arg passing, add gradient clipping support.
|
4 years ago |
|
Ross Wightman
|
fcb6258877
|
Add missing leaky_relu layer factory defn, update Apex/Native loss scaler interfaces to support unscaled grad clipping. Bump ver to 0.2.2 for pending release.
|
4 years ago |
|
Ross Wightman
|
186075ef03
|
Merge pull request #244 from hollance/master
Bug fix: test_time_pool would be set to a non-False value
|
4 years ago |
|
Matthijs Hollemans
|
f04bdc8c8e
|
don't forget this file
|
4 years ago |
|
Matthijs Hollemans
|
8ffdc5910a
|
test_time_pool would be set to a non-False value even if test-time pooling is not available
|
4 years ago |
|
Ross Wightman
|
4be5b51e0a
|
Missed moving some seresnet -> legacy in sotabench. Check sotabench cache.
|
4 years ago |
|
Ross Wightman
|
e8e2d9cabf
|
Add DropPath (stochastic depth) to ReXNet and VoVNet. RegNet DropPath impl tweak and dedupe se args.
|
4 years ago |
|
Ross Wightman
|
e8ca45854c
|
More models in sotabench, more control over sotabench run, dataset filename extraction consistency
|
4 years ago |
|
Ross Wightman
|
9c406532bd
|
Add EfficientNet-EdgeTPU-M (efficientnet_em) model trained natively in PyTorch. More sotabench fiddling.
|
4 years ago |
|
Ross Wightman
|
3681c5c4dd
|
Another sotabench.py debug iter
|
4 years ago |
|
Ross Wightman
|
08029852d9
|
Sotabench debugging
|
4 years ago |
|
Ross Wightman
|
c40384f5bd
|
Add ResNet weights. 80.5 (top-1) ResNet-50-D, 77.1 ResNet-34-D, 72.7 ResNet-18-D.
|
4 years ago |
|
Ross Wightman
|
e39bf6ef59
|
Merge pull request #237 from rwightman/utils_cleanup
Utils refactor, more cutmix modes / change mode arg
|
4 years ago |
|
Ross Wightman
|
47a7b3b5b1
|
More flexible mixup mode, add 'half' mode.
|
4 years ago |
|
Ross Wightman
|
532e3b417d
|
Reorg of utils into separate modules
|
4 years ago |
|
Ross Wightman
|
9ce42d5c5a
|
Update README.md
|
4 years ago |
|
Ross Wightman
|
0729dbe865
|
Update README.md
|
4 years ago |
|
Ross Wightman
|
33f8a1bf36
|
Updated README, add wide_resnet50_2 and seresnext50_32x4d weights
|
4 years ago |
|
Ross Wightman
|
5247eb37a7
|
Merge pull request #233 from rwightman/torchamp
Native Torch AMP and channels_last support for train.py and validate.py
|
4 years ago |
|
Ross Wightman
|
751b0bba98
|
Add global_pool (--gp) arg changes to allow passing 'fast' easily for train/validate to avoid channels_last issue with AdaptiveAvgPool
|
4 years ago |
|
Ross Wightman
|
9c297ec67d
|
Cleanup Apex vs native AMP scaler state save/load. Cleanup CheckpointSaver a bit.
|
4 years ago |
|
Ross Wightman
|
80c9d9cc72
|
Add 'fast' global pool option, remove redundant SEModule from tresnet, normal one is now 'fast'
|
4 years ago |
|
Ross Wightman
|
90a01f47d1
|
hrnet features_only pretrained weight loading issue. Fix #232.
|
4 years ago |
|
Ross Wightman
|
110a7c4982
|
AdaptiveAvgPool2d -> mean((2,3)) for all SE/attn layers to avoid NaN with AMP + channels_last layout. See https://github.com/pytorch/pytorch/issues/43992
|
4 years ago |
|
Ross Wightman
|
c2cd1a332e
|
Improve torch amp support and add channels_last support for train/validate scripts
|
4 years ago |
|
Ross Wightman
|
1d34a0a851
|
Merge branch 'master' of https://github.com/tgisaturday/pytorch-image-models into torchamp
|
4 years ago |
|
Ross Wightman
|
6d158adfe9
|
Update README.md
|
4 years ago |
|
datamining99
|
5f563ca4df
|
fix save_checkpoint bug with native amp
|
4 years ago |
|
datamining99
|
d98967ed5d
|
add support for native torch AMP in torch 1.6
|
4 years ago |
|
Ross Wightman
|
470220b1f4
|
Fix MobileNetV3 crash with global_pool='', output consistent with other models but not equivalent due to efficient head.
|
4 years ago |
|
Ross Wightman
|
fc8b8afb6f
|
Fix a silly bug in Sample version of EvoNorm missing x* part of swish, update EvoNormBatch to accumulated unbiased variance.
|
4 years ago |
|
Ross Wightman
|
fa26f6c1cf
|
Update README.md
|
4 years ago |
|
Ross Wightman
|
f614df7921
|
Bump version to 0.2.1 and update README
|
4 years ago |
|
Ross Wightman
|
b423bc8362
|
Merge pull request #218 from rwightman/cutmix
CutMix + MixUp overhaul
|
4 years ago |
|
Ross Wightman
|
8c9814e3f5
|
Final cleanup of mixup/cutmix. Element/batch modes working with both collate (prefetcher active) and without prefetcher.
|
4 years ago |
|
Ross Wightman
|
0f5d9d8166
|
Add CSPResNet50 weights, 79.6 top-1 at 256x256
|
4 years ago |
|
Ross Wightman
|
0734c0d187
|
Update test workflow
|
4 years ago |
|
Ross Wightman
|
b1b6e7c361
|
Fix a few more issues related to #216 w/ TResNet (space2depth) and FP16 weights in wide resnets. Also don't completely dump pretrained weights in in_chans != 1 or 3 cases.
|
4 years ago |
|
Ross Wightman
|
512b2dd645
|
Add new EfficientNet-B3 and RegNetY-3.2GF weights, both just over 82 top-1
|
4 years ago |
|
Ross Wightman
|
6890300877
|
Add DropPath (stochastic depth) to RegNet
|
4 years ago |
|
Ross Wightman
|
47794d2c59
|
Merge pull request #216 from yu4u/fix_default_cfgs
Fix default_cfgs for first conv
|
4 years ago |
|
Ross Wightman
|
cd23f55397
|
Fix mixed prec issues with new mixup code
|
4 years ago |
|
Yusuke Uchida
|
e717250ed4
|
remove comments
|
4 years ago |
|
Yusuke Uchida
|
f6b56602f9
|
fix test_model_default_cfgs
|
4 years ago |
|
Ross Wightman
|
f471c17c9d
|
More cutmix/mixup overhaul, ready to kick-off some trials.
|
4 years ago |
