8880f696b6
Refactoring, cleanup, improved test coverage.
...
* Add eca_nfnet_l2 weights, 84.7 @ 384x384
* All 'non-std' (ie transformer / mlp) models have classifier / default_cfg test added
* Fix #694 reset_classifer / num_features / forward_features / num_classes=0 consistency for transformer / mlp models
* Add direct loading of npz to vision transformer (pure transformer so far, hybrid to come)
* Rename vit_deit* to deit_*
* Remove some deprecated vit hybrid model defs
* Clean up classifier flatten for conv classifiers and unusual cases (mobilenetv3/ghostnet)
* Remove explicit model fns for levit conv, just pass in arg
3 years ago
ba2ca4b464
One codepath for stdconv, switch layernorm to batchnorm so gain included. Tweak epsilon values for nfnet, resnetv2, vit hybrid.
3 years ago
07fb05cc3d
Update results csv files
3 years ago
b79dfd4fc2
Merge pull request #693 from SamuelGabriel/patch-1
...
Let only the _globally_ 0th rank write checkpoints in `train.py`
3 years ago
7c19c35d9f
Global instead of local rank.
3 years ago
b7a568f065
Fix torchscript issue in bat
3 years ago
d17b374f0f
Minimum input_size needed to be higher
3 years ago
b3b90d944d
Add min_input_size to bat_resnext to prevent test breakage.
3 years ago
758c4438a7
Update README.md
3 years ago
d413eef1bf
Add ResMLP-24 model weights that I trained in PyTorch XLA on TPU-VM. 79.2 top-1.
3 years ago
10d8fa4620
Add gc and bat attention resnext26ts variants to byob for test.
3 years ago
2f5ed2dec1
Update `init_values` const for 24 and 36 layer ResMLP models
3 years ago
8e4ac3549f
All ScaledStdConv and StdConv uses default to using F.layernorm so that they work with PyTorch XLA. eps value tweaking is a WIP.
3 years ago
2a63d0246b
Post merge cleanup
3 years ago
45dec179e5
Merge pull request #681 from lmk123568/master
...
Update convit.py
3 years ago
4907f8f70d
Merge pull request #685 from dyhan0920/master
...
Update rexnet.py
3 years ago
ded1671483
Fix stochastic depth working only with a shortcut
3 years ago
b87d98b238
Update convit.py
...
Cut out the duplicates
4 years ago
54a6cca27a
Merge pull request #668 from rwightman/more_attn
...
Add Gather-Excite, Global Context, BAT, Non-Local attn modules and refactored all attn modules and factory for improved consistency. EfficientNet / MobileNetV3 backbones able to use a wider variety of attention modules.
4 years ago
02320c3e3d
Bump version to 0.4.11
4 years ago
bda8ab015a
Remove min channels for SelectiveKernel, divisor should cover cases well enough.
4 years ago
a27f4aec4a
Missed args for skresnext w/ refactoring.
4 years ago
307a935b79
Add non-local and BAT attention. Merge attn and self-attn factories into one. Add attention references to README. Add mlp 'mode' to ECA.
4 years ago
17dc47c8e6
Missed comma in test filters.
4 years ago
34522097b1
See if we can use tcmalloc in test runner
4 years ago
8bf63b6c6c
Able to use other attn layer in EfficientNet now. Create test ECA + GC B0 configs. Make ECA more configurable.
4 years ago
bcec14d3b5
Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.
4 years ago
9611458e19
Throw in some FBNetV3 code I had lying around, some refactoring of SE reduction channel calcs for all EffNet archs.
4 years ago
01b9108619
Merge branch 'master' into more_attn
4 years ago
d7bab8a6c5
Fix strict flag change for checkpoint load.
4 years ago
02f9d4bc34
Add weights for resnet51q model, add 61q def.
4 years ago
f615474be3
Fix broken test, repvgg block doesn't have attn_last attr.
4 years ago
742c2d5247
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
4 years ago
9c78de8c02
Fix #661 , move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present.
4 years ago
07d952c7a7
Merge pull request #637 from rwightman/levit_visformer_rednet
...
LeVit, Visformer, RedNet/Involution models and layers
4 years ago
7f368782b7
Merge pull request #660 from petervandenabeele/readme_fix_typos
...
README: fix simple typos
4 years ago
5db7452173
Fix visformer in_chans stem handling
4 years ago
51c432150a
README: fix simple typos
4 years ago
fd92ba0de8
Filter large vit models from torchscript tests
4 years ago
318360c3f9
Update README.md before merge. Bump version to 0.4.10
4 years ago
99d97e0d67
Hopefully the last test update for this PR...
4 years ago
11ae795e99
Redo LeViT attention bias caching in a way that works with both torchscript and DataParallel
4 years ago
d400f1dbdd
Filter test models before creation for backward/torchscript tests
4 years ago
c4572cc5aa
Add Visformer-small weighs, tweak torchscript jit test img size.
4 years ago
83487e2a0d
Lower max backward size for tests.
4 years ago
bfc72f75d3
Expand scope of testing for non-std vision transformer / mlp models. Some related cleanup and create fn cleanup for all vision transformer and mlp models. More CoaT weights.
4 years ago
18bf520ad1
Add eca_nfnet_l2/l3 defs for future training
4 years ago
f45de37690
Merge branch 'master' into levit_visformer_rednet
4 years ago
23c18a33e4
Add efficientnetv2_rw_m weights trained in PyTorch. 84.8 top-1 @ 416 test. 53M params.
4 years ago
c2ba229d99
Prep for effcientnetv2_rw_m model weights that started training before official release..
4 years ago
Ross Wightman