Aman Arora
|
e7df94a760
|
Merge branch 'master' into resnet-rs
|
4 years ago |
morizin
|
06841427cd
|
Add files via upload
|
4 years ago |
Ross Wightman
|
d793deb51a
|
Merge branch 'master' of https://github.com/iamhankai/pytorch-image-models into iamhankai-master
|
4 years ago |
Ross Wightman
|
277a9a78f9
|
Fix unit test filter update.
|
4 years ago |
Ross Wightman
|
858728799c
|
Update README again. Add 101x3 BiT-M model to CI ignore since it's starting to fail in GitHub runners.
|
4 years ago |
Ross Wightman
|
f606c45c38
|
Add Swin Transformer models from https://github.com/microsoft/Swin-Transformer
|
4 years ago |
iamhankai
|
de445e7827
|
Add GhostNet
|
4 years ago |
Ross Wightman
|
16f7aa9f54
|
Add default_cfg options for min_input_size / fixed_input_size, queries in model registry, and use for testing self-attn models
|
4 years ago |
Aman Arora
|
ea9f935e9d
|
Remove resnetv2_101x1_bitm from exclude feat features
|
4 years ago |
Aman Arora
|
3a73401b5d
|
Add bigger resnetrs to model filters to fix Github CLI
|
4 years ago |
Aman Arora
|
59ca94572b
|
Run all tests
|
4 years ago |
Aman Arora
|
607672841b
|
run all tests
|
4 years ago |
Aman Arora
|
84fd045e4d
|
only run test_forward_features
|
4 years ago |
Aman Arora
|
a17ce022e6
|
back to defaults
|
4 years ago |
Aman Arora
|
f89bf2c752
|
Add to exclude ftrs
|
4 years ago |
Aman Arora
|
094f04d992
|
Run test_model_forward_features for all
|
4 years ago |
Aman Arora
|
bf63f0cc7b
|
Add to exclude filter
|
4 years ago |
Aman Arora
|
973b8801c4
|
Try running only resnetv2_101x1_bitm on Linux runner
|
4 years ago |
Aman Arora
|
823162c4af
|
increase time
|
4 years ago |
Aman Arora
|
3df71a1625
|
Update time
|
4 years ago |
Ross Wightman
|
2b49ab7a36
|
Fix ResNetV2 pretrained classifier issue. Fixes #540
|
4 years ago |
Ross Wightman
|
0dfc5a66bb
|
Add PiT model from https://github.com/naver-ai/pit
|
4 years ago |
Ross Wightman
|
51febd869b
|
Small tweak to tests for tnt model, reorder model imports.
|
4 years ago |
contrastive
|
809271b0f3
|
Update test_models.py
|
4 years ago |
Ross Wightman
|
317ea3e599
|
Tweak NFNet, ResNetV2, RexNet feature extraction, use pre-act features for simplicty. Update tests for pytorch 1.8. 0.4.5 version bump.
|
4 years ago |
Ross Wightman
|
da4839530c
|
Fix test model filter to include dm_ variants that break GitHub CI limits
|
4 years ago |
Ross Wightman
|
0d253e2c5e
|
Fix issue with nfnet tests, bit more cleanup.
|
5 years ago |
Ross Wightman
|
9811e229f7
|
Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.
|
5 years ago |
Ross Wightman
|
55f7dfa9ea
|
Refactor vision_transformer entrpy fns, add pos embedding resize support for fine tuning, add some deit models for testing
|
5 years ago |
Ross Wightman
|
0a1668f63e
|
Update tests
|
5 years ago |
Ross Wightman
|
20516abc18
|
Fix some broken tests for ResNetV2 BiT models
|
5 years ago |
Ross Wightman
|
2ed8f24715
|
A few more changes for 0.3.2 maint release. Linear layer change for mobilenetv3 and inception_v3, support no bias for linear wrapper.
|
5 years ago |
Ross Wightman
|
da6cd2cc1f
|
Fix regression for pretrained classifier loading when using entrypt functions directly
|
5 years ago |
Ross Wightman
|
be53107e8a
|
Update README, ensure vit excluded from all tests (not ready)
|
5 years ago |
Ross Wightman
|
f31933cb37
|
Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.
|
5 years ago |
Ross Wightman
|
90a01f47d1
|
hrnet features_only pretrained weight loading issue. Fix #232.
|
5 years ago |
Ross Wightman
|
470220b1f4
|
Fix MobileNetV3 crash with global_pool='', output consistent with other models but not equivalent due to efficient head.
|
5 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.
|
5 years ago |
Yusuke Uchida
|
e717250ed4
|
remove comments
|
5 years ago |
Yusuke Uchida
|
f6b56602f9
|
fix test_model_default_cfgs
|
5 years ago |
Ross Wightman
|
d5145fa4d5
|
Change default_cfg names for senet to include the legacy and match model names
|
5 years ago |
Ross Wightman
|
b1f1a54de9
|
More uniform treatment of classifiers across all models, reduce code duplication.
|
5 years ago |
Ross Wightman
|
d72ddafe56
|
Fix some checkpoint / model str regressions
|
5 years ago |
Ross Wightman
|
ea58e0bc16
|
Disable big models for MacOS test since they are starting to fail frequently.
|
5 years ago |
Ross Wightman
|
7ba5a384d3
|
Add ReXNet w/ remapped weights, feature support
|
5 years ago |
Ross Wightman
|
c9d54bc1c3
|
Add HRNet feature extraction, fix senet type, lower feature testing res to 96x96
|
5 years ago |
Ross Wightman
|
2ac663f340
|
Add feature support to legacy senets, add 32x32 resnext models to exclude list for feature testing.
|
5 years ago |
Ross Wightman
|
4e61c6a12d
|
Cleanup, refactoring of Feature extraction code, add tests, fix tests, non hook feature extraction working with torchscript
|
5 years ago |
Ross Wightman
|
9eba134d79
|
More models supporting feature extraction, xception, gluon_xception, inception_v3, inception_v4, pnasnet, nasnet, dla. Fix DLA unused projection params.
|
5 years ago |
Ross Wightman
|
151679c2f1
|
Add custom grad tests, fix cut & paste error with hard_mish ME, add a few more pytorch act fns to factory
|
5 years ago |