Ross Wightman
303f7691a1
Add cautious mars, improve test reliability by skipping grad diff for first step
2024-12-02 11:29:02 -08:00
Ross Wightman
7cf683628f
Cautious optimizer impl plus some typing cleanup.
2024-11-28 15:11:58 -08:00
Ross Wightman
aeb1ed7a15
Keep basic optim test LR range closer to before w/ updated code
2024-11-26 15:10:15 -08:00
Ross Wightman
7a165fcb62
Remove rogue import, thanks IDE :/
2024-11-26 15:10:15 -08:00
Ross Wightman
73d10ab482
Update tests, need handling for radamw with older PyTorch, need to back-off basic test LR in mars?
2024-11-26 15:10:15 -08:00
Ross Wightman
0903d98162
Reduce tolerance on model inference 'owl' test, pillow output varies a lot, was failing locally
2024-11-26 15:10:15 -08:00
Ross Wightman
a024ab3170
Replace radam & nadam impl with torch.optim ver, rename legacy adamw, nadam, radam impl in timm. Update optim factory & tests.
2024-11-26 15:10:15 -08:00
Ross Wightman
0b5264a108
Missing optimizers in __init__.py, add bind_defaults=False for unit tests
2024-11-13 10:50:46 -08:00
Ross Wightman
dde990785e
More fixes for new factory & tests, add back adahessian
2024-11-12 20:49:01 -08:00
Ross Wightman
45490ac52f
Post merge fix reference of old param groups helper fn locations
2024-11-12 20:49:01 -08:00
Ross Wightman
ee5f6e76bb
A bit of an optimizer overhaul, added an improved factory, list_optimizers, class helper and add info classes with descriptions, arg configs
2024-11-12 20:49:01 -08:00
Ross Wightman
94e0560aba
Remove an indent level in init_group for adopt, update optim tests, adopt failing rosenbrock
2024-11-12 20:49:01 -08:00
mrT23
e31e5d2d64
imports
2024-11-12 07:53:39 -08:00
Tal
68d5a64e45
extend existing unittests
2024-11-12 07:53:39 -08:00
Ross Wightman
95907e69c2
Further reduce atol for model comparison, move python 3.11 + torch 2.2 -> python 3.12 + torch 2.4.1
2024-10-02 10:05:27 -07:00
Ross Wightman
fde6719403
relax tolerance on inference test
2024-10-02 09:53:17 -07:00
Ross Wightman
0e27f302a0
Do full inference test against test vectors for test_* models
2024-10-02 09:39:26 -07:00
Ross Wightman
0b05122cda
Fixing hieradet (sam2) tests
2024-08-16 14:33:40 -07:00
Ross Wightman
f920119f3b
Fixing tests
2024-07-09 14:53:20 -07:00
Daniel Suess
197c10463b
Fix jit.script breaking with features_fx
2024-06-28 03:58:51 +00:00
Ross Wightman
a5a2ad2e48
Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size
...
* add test that model supports forward_head(x, pre_logits=True)
* add head_hidden_size attr to all models and set differently from num_features attr when head has hidden layers
* test forward_features() feat dim == model.num_features and pre_logits feat dim == self.head_hidden_size
* more consistency in reset_classifier signature, add typing
* asserts in some heads where pooling cannot be disabled
Fix #2194
2024-06-07 13:53:00 -07:00
Ross Wightman
5756a81c55
Merge remote-tracking branch 'origin/Beckschen-vitamin' into fastvit_mobileclip
2024-06-05 15:20:54 -07:00
Ross Wightman
0e77c95ed7
Add vitamin to non-std testing models
2024-06-05 00:20:00 -07:00
Ross Wightman
ce637771dc
Add fastvit to forward_intermediates test
2024-05-30 10:18:24 -07:00
Ross Wightman
2ca45a4ff5
Merge remote-tracking branch 'upstream/main' into hiera
2024-05-11 15:43:05 -07:00
Ross Wightman
45b7ae8029
forward_intermediates() support for byob/byoanet models
2024-05-04 14:06:52 -07:00
Ross Wightman
c719f7eb86
More forward_intermediates() updates
...
* add convnext, resnet, efficientformer, levit support
* remove kwargs only for fn so that torchscript isn't broken for all :(
* use reset_classifier() consistently in prune
2024-05-03 16:22:32 -07:00
Ross Wightman
d6da4fb01e
Add forward_intermediates() to efficientnet / mobilenetv3 based models as an exercise.
2024-05-02 14:19:16 -07:00
Ross Wightman
67332fce24
Add features_intermediate() support to coatnet, maxvit, swin* models. Refine feature interface. Start prep of new vit weights.
2024-04-30 16:56:33 -07:00
Ross Wightman
63970e4e61
Update tests for volo/cait/xcit forward_intermediates
2024-04-29 17:19:11 -07:00
Ross Wightman
e8b08a4e7b
Disable jit test for Hiera, fair bit of work to fix.
2024-04-22 10:39:30 -07:00
Ross Wightman
ef147fd2fb
Add forward_intermediates API to Hiera for features_only=True support
2024-04-21 11:30:41 -07:00
Ross Wightman
fe3cf542fa
Fix / improve tests for features
2024-04-10 21:14:02 -07:00
Ross Wightman
4b2565e4cb
More forward_intermediates() / FeatureGetterNet work
...
* include relpos vit
* refactor reduction / size calcs so hybrid vits work and dynamic_img_size works
* fix -ve feature indices when pruning
* fix mvitv2 w/ class token
* refine naming
* add tests
2024-04-10 15:11:34 -07:00
Alex Cunha
a38c2b4475
fix bug
2023-11-16 20:27:59 -08:00
Alex Cunha
bbf0ab000c
return if cuda not available
2023-11-16 20:27:59 -08:00
Alex Cunha
e628ed7e67
device agnostic testing
2023-11-16 20:27:59 -08:00
Ross Wightman
68b2824e49
Update optim test to remove Variable/.data and fix _state_dict optim test for PyTorch 2.1 ( #1988 )
...
* Update optim test to remove Variable/.data and fix _state_dict optim test
* Attempt to run python 3.11 w/ 2.1
* Try factoring out testmarker to common var
* More fiddling
* Abandon attempt to reduce redunancy
* Another try
2023-10-12 11:53:10 -07:00
方曦
0198a2019e
tinyvit skip ci test
2023-09-01 11:05:56 -07:00
Ross Wightman
7c2728c6fe
Merge pull request #1919 from ChengpengChen/main
...
Add RepGhost models and weights
2023-08-19 16:26:45 -07:00
方曦
00f670fa69
fix bug in ci for efficientvits
2023-08-17 14:40:17 +08:00
Chengpeng Chen
d1d0193615
Add RepGhost models and weights
2023-08-16 11:54:53 +08:00
方曦
15de561f2c
fix unit test for samvit
2023-05-17 12:51:12 +08:00
Ross Wightman
3386af8c86
Final push to get remaining models using multi-weight pretrained configs, almost all weights on HF hub
2023-04-26 15:52:13 -07:00
Ross Wightman
067c7281e2
Another test filter adjustment
2023-03-31 08:33:26 -07:00
Ross Wightman
3825812f1a
Update test filtering for enormoous
2023-03-31 00:04:56 -07:00
Ross Wightman
a84abe6656
Add eva02 to non-std test models
2023-03-27 22:56:52 -07:00
Ross Wightman
b3e816d6d7
Improve filtering behaviour for tag + non-tagged model wildcard consistency.
2023-03-22 10:21:22 -07:00
Ross Wightman
2fc5ac3d18
Exclude the large models from default_cfgs, failing github CI
2023-03-16 14:51:20 -07:00
Ross Wightman
acfd85ad68
All swin models support spatial output, add output_fmt to v1/v2 and use ClassifierHead.
...
* update ClassifierHead to allow different input format
* add output format support to patch embed
* fix some flatten issues for a few conv head models
* add Format enum and helpers for tensor format (layout) choices
2023-03-15 23:21:51 -07:00
