ef9c6fb846
forward_head(), consistent pre_logits handling to reduce likelihood of people manually replacing .head module having issues
2024-04-09 21:54:59 -07:00
679daef76a
More forward_intermediates() & features_only work
...
* forward_intermediates() added to beit, deit, eva, mvitv2, twins, vit, vit_sam
* add features_only to forward intermediates to allow just intermediate features
* fix #2060
* fix #1374
* fix #657
2024-04-09 21:29:16 -07:00
c28ee2e904
Merge pull request #2145 from huggingface/fix_imagenet22k_ms_mapping
...
Add teddy-bear class back to first 1000 classes of imagenet22k_ms_synsets (line 851, index 850)
2024-04-09 14:56:31 -07:00
f5ea076a46
Merge pull request #2143 from huggingface/fix_asymm_set_grad_enable
...
Fix #2132 , remove use of _C.set_grad_enable. Line endings were messed up too
2024-04-09 10:14:13 -07:00
286d941923
Add teddy-bear class back to first 1000 classes of imagenet22k_ms_synsets (index 851)
2024-04-09 09:33:08 -07:00
5c5ae8d401
Fix #2132 , remove use of _C.set_grad_enable. Line endings were messed up too
2024-04-09 09:00:23 -07:00
17b892f703
Fix #2139 , disable strict weight loading when head changes from classification
2024-04-09 08:41:37 -07:00
5fdc0b4e93
Exploring vit features_only using get_intermediate_layers() as per #2131
2024-04-07 11:24:45 -07:00
b44e4e45a2
more
2024-04-02 10:25:30 +08:00
8880a5cd5c
Update scheduler.py
2024-03-23 11:27:33 +08:00
34b41b143c
Fiddling with efficientnet x/h defs, is it worth adding & training any?
2024-03-22 17:55:02 -07:00
c559c3911f
Improve vit conversions. OpenAI convert pass through main convert for patch & pos resize. Fix #2120
2024-03-21 10:00:43 -07:00
256cf19148
Rename tinyclip models to fit existing 'clip' variants, use consistently mapped OpenCLIP compatible checkpoint on hf hub
2024-03-20 15:21:46 -07:00
1a1d07d479
add other tinyclip
2024-03-19 07:27:09 +08:00
dfffffac55
add tinyclip 8m
2024-03-19 07:02:17 +08:00
6ccb7d6a7c
Merge pull request #2111 from jamesljlster/enhance_vit_get_intermediate_layers
...
Vision Transformer (ViT) get_intermediate_layers: enhanced to support dynamic image size and saved computational costs from unused blocks
2024-03-18 13:41:18 -07:00
db06b56d34
Saved computational costs of get_intermediate_layers() from unused blocks
2024-03-17 21:34:06 +08:00
4731e4efc4
Modified ViT get_intermediate_layers() to support dynamic image size
2024-03-16 23:07:21 +08:00
ba641e07ae
Add support for dynamo based onnx export
2024-03-13 12:05:26 -07:00
59cb0be595
SwinV2: add configurable act_layer argument
...
Defaults to "gelu", but makes it possible to pass "gelu_tanh".
Makes it easier to port weights from JAX/Flax, where the tanh
approximation is the default.
2024-03-05 22:04:17 +01:00
49992b0dc7
Update version.py
...
Update to 0.9.16 for release
2024-02-19 11:08:17 -08:00
35d6eef0df
Version bump, add test markers back to toml
2024-02-16 09:04:00 -08:00
31e0dc0a5d
Tweak hgnet before merge
2024-02-12 15:00:32 -08:00
3e03491e49
Merge branch 'master' of https://github.com/seefun/pytorch-image-models into seefun-master
2024-02-12 14:59:54 -08:00
958938845a
Update version.py
2024-02-10 23:10:50 -08:00
47c9bc4dc6
Fix device idx split
2024-02-10 21:41:14 -08:00
59239d9df5
Cleanup imports for vit relpos
2024-02-10 21:40:57 -08:00
ac1b08deb6
fix_init on vit & relpos vit
2024-02-10 20:15:37 -08:00
935950cc11
Fix F.sdpa attn drop prob
2024-02-10 20:14:47 -08:00
0737cf231d
Add Next-ViT
2024-02-10 17:05:16 -08:00
d6c2cc91af
Make NormMlpClassifier head reset args consistent with ClassifierHead
2024-02-10 16:25:33 -08:00
87fec3dc14
Update experimental vit model configs
2024-02-10 16:05:58 -08:00
7d3c2dc993
Add group_matcher for DaViT
2024-02-10 14:58:45 -08:00
7bc7798d0e
Type annotation correctness for create_act
2024-02-10 14:57:58 -08:00
7d121ac2ef
Small tweak of timm ToTensor for clarity
2024-02-10 14:57:40 -08:00
a08b57e801
Fix distributed flag bug w/ flex device handling
2024-02-03 16:26:15 -08:00
bee0471f91
forward() pass through for ema model, flag for ema warmup, comment about warmup
2024-02-03 16:24:45 -08:00
5e4a4b2adc
Merge branch 'device_flex' into mesa_ema
2024-02-02 09:45:30 -08:00
dd84ef2cd5
ModelEmaV3 and MESA experiments
2024-02-02 09:45:04 -08:00
d0ff315eed
Merge remote-tracking branch 'emav3/faster_ema' into mesa_ema
2024-01-27 14:52:10 -08:00
88889de923
Fix meshgrid deprecation warnings and backward compat with explicit 'ndgrid' and 'meshgrid' fn w/o indexing arg
2024-01-27 13:48:33 -08:00
d4386219c6
Improve type handling for arange & rel pos embeds, keep calculations in float32 until application (may change to apply in float32 in future). Prevent arange type hijacking by DeepSpeed Zero
2024-01-26 16:35:51 -08:00
3234daf783
Add missing deprecation mapping for a densenet and xcit model. Fix #2086 . Tweak xcit pos embed use of arange for better low prec safety.
2024-01-24 22:04:04 -08:00
809a9e14e2
Pass train-crop-mode to create_loader/transforms from train.py args
2024-01-24 16:19:02 -08:00
a48ab818f5
Improving device flexibility in train. Fix #2081
2024-01-20 15:10:20 -08:00
53a4888328
Add droppath and type hint to Xception.
2024-01-19 11:15:47 -08:00
7f19a4cce7
fix fast catavgmax selection
2024-01-16 10:30:08 -08:00
2eac2f6955
Fiddling with iterator wrapping for HF ds streaming
2024-01-09 12:41:54 -08:00
992976f007
Update version.py
2024-01-08 09:39:22 -08:00
c50004db79
Allow training w/o validation split set
2024-01-08 09:38:42 -08:00
be0944edae
Significant transforms, dataset, dataloading enhancements.
2024-01-08 09:38:42 -08:00
b5a4fa9c3b
Add pos_weight and support for summing over classes to BCE impl in train scripts
2023-12-30 12:13:06 -08:00
9dbea3bef6
fix cls head in hgnet
2023-12-27 21:26:26 +08:00
56ae8b906d
fix reset head in hgnet
2023-12-27 20:11:29 +08:00
6862c9850a
fix backward in hgnet
2023-12-27 16:49:37 +08:00
6cd28bc5c2
Merge branch 'huggingface:main' into master
2023-12-27 16:43:37 +08:00
f2fdd97e9f
Add parsable json results output for train.py, tweak --pretrained-path to force head adaptation
2023-12-22 11:18:25 -08:00
e0079c92da
Update eva.py ( #2058 )
...
* Update eva.py
When argument class token = False, self.cls_token = None.
Prevents error from attempting trunc_normal_ on None:
AttributeError: 'NoneType' object has no attribute 'uniform_'
* Update eva.py
fix
2023-12-16 15:10:45 -08:00
7da34a999a
add type annotations in the code of swin_transformer_v2
2023-12-15 09:31:25 -08:00
bbe798317f
Update EdgeNeXt to use ClassifierHead as per ConvNeXt ( #2051 )
...
* Update edgenext.py
2023-12-11 12:17:19 -08:00
711c5dee6d
Update sgdw for older pytorch
2023-12-11 12:10:29 -08:00
60b170b200
Add --pretrained-path arg to train script to allow passing local checkpoint as pretrained. Add missing/unexpected keys log.
2023-12-11 12:10:29 -08:00
17a47c0e35
Add SGDW optimizer
2023-12-11 12:10:29 -08:00
2597ce2860
Update davit.py
2023-12-11 11:13:04 -08:00
2bd043ce5d
fix doc position
2023-12-05 12:00:51 -08:00
4f2e1bf4cb
Add missing docs in SwinTransformerStage
2023-12-05 12:00:51 -08:00
df7ae11eb2
Add device arg for patch embed resize, fix #2024
2023-12-04 11:42:13 -08:00
cd8d9d9ff3
Add missing hf hub entries for mvitv2
2023-11-26 21:06:39 -08:00
19a8c182cc
Version 0.9.13dev0
2023-11-25 10:52:31 -08:00
b996c1a0f5
A few more missed hf hub entries
2023-11-23 21:48:14 -08:00
5fb92d79e7
Version 0.9.12
2023-11-23 17:01:03 -08:00
89ec91aece
Add missing hf_hub entry for mobilnetv3_rw
2023-11-23 12:44:59 -08:00
40d55ab4bc
Add `in_chans` to data config helper. Fix #2021
2023-11-23 12:44:59 -08:00
63ee54853c
fixed intermediate output indices
2023-11-22 16:32:41 -08:00
fa06f6c481
Merge branch 'seefun-efficientvit'
2023-11-21 14:06:27 -08:00
c6b0c98963
Upload weights to hub, tweak crop_pct, comment out SAM EfficientViTs for now (v2 weights comming)
2023-11-21 14:05:04 -08:00
975203a369
Version 0.9.12dev0
2023-11-21 10:18:45 -08:00
ada145b016
Literal use w/ python < 3.8 requires typing_extension, cach instead of check sys ver
2023-11-21 09:48:03 -08:00
dfaab97d20
More consistency in model arg/kwarg merge handling
2023-11-21 09:48:03 -08:00
3775e4984f
Merge branch 'efficientvit' of github.com:seefun/pytorch-image-models into seefun-efficientvit
2023-11-20 16:21:38 -08:00
dfb8658100
Fix a few missed model deprecations and one missed pretrained cfg
2023-11-20 12:41:49 -08:00
c20f5fc385
Version 0.9.11
2023-11-19 17:18:48 -08:00
a604011935
Add support for passing model args via hf hub config
2023-11-19 15:16:01 -08:00
c9d093a58e
update norm eps for efficientvit large
2023-11-18 17:46:47 +08:00
21647c0a0c
Add types to vision_transformers.py
2023-11-17 16:06:06 -08:00
87ba43a9bc
add efficientvit large series
2023-11-17 13:58:46 +08:00
7c685a4ef3
Fix openai quickgelu loading and add mnissing orig_in21k vit weights and remove zero'd classifier w/ matching hub update
2023-11-16 19:16:28 -08:00
ef72c3cd47
Add warnings for duplicate registry names
2023-11-08 10:18:59 -08:00
205d8ad37c
version 0.9.10
2023-11-04 02:33:04 -07:00
9fab8d8f58
Fix break of 2 years old torchvision installs :/
2023-11-04 02:32:09 -07:00
d3e83a190f
Add in12k fine-tuned convnext_xxlarge
2023-11-03 14:35:01 -07:00
855719fca6
Prep for 0.9.9 release
2023-11-03 11:38:09 -07:00
f7762fee78
Consistency handling None / empty string inputs to norm / act create fns
2023-11-03 11:01:41 -07:00
dcfdba1f5f
Make quickgelu models appear in listing
2023-11-03 11:01:41 -07:00
96bd162ddb
Add cc-by-nc-4.0 license for metaclip, make note in quickgelu model def about pretrained_cfg mapping
2023-11-03 11:01:41 -07:00
6894ec7edc
Forgot about datcomp b32 models
2023-11-03 11:01:41 -07:00
a2e4a4c148
Add quickgelu vit clip variants, simplify get_norm_layer and allow string args in vit norm/act. Add metaclip CLIP weights
2023-11-03 11:01:41 -07:00
c55bc41a42
DFN CLIP ViT support
2023-10-31 12:16:21 -07:00
d5f1525334
include suggestions from review
...
Co-Authored-By: Ross Wightman <rwightman@gmail.com>
2023-10-30 13:47:54 -07:00
5f14bdd564
include typing suggestions by @rwightman
2023-10-30 13:47:54 -07:00
05b0aaca51
improvement: add typehints and docs to timm/models/resnet.py
2023-10-30 13:47:54 -07:00
c2fe0a2268
improvement: add typehints and docs to timm/models/mobilenetv3.py
2023-10-30 13:47:54 -07:00
d023154bb5
Update swin_transformer.py
...
make `SwimTransformer`'s `patch_embed` customizable through the constructor
2023-10-30 13:47:14 -07:00
68a121402f
Added hub weights for dinov2 register models
2023-10-29 23:03:48 -07:00
3f02392488
Add DINOv2 models with register tokens. Convert pos embed to non-overlapping for consistency.
2023-10-29 23:03:48 -07:00
fe92fd93e5
fix adaptive_avgmax_pool.py
...
remove extra whitespace in `SelectAdaptivePool2d`'s `__repr__`
2023-10-29 23:03:36 -07:00
97450d618a
Update DINOv2 license to Apache 2.0
2023-10-27 09:12:51 -07:00
7a6369156f
avoid getting undefined
2023-10-22 21:36:23 -07:00
89ba0da910
Fixed Typos
...
Fixed the typos in helpers.py and CONTRIBUTING.md
2023-10-21 21:46:31 -07:00
9afe0bb78e
Update README, prep for 0.9.8 release
2023-10-20 13:57:23 -07:00
8556462a18
fix doc typo in resnetv2
2023-10-20 11:56:50 -07:00
462fb3ec9f
Push new repvit weights to hub, tweak tag names
2023-10-20 11:49:29 -07:00
5309424d5e
Merge branch 'main' of https://github.com/jameslahm/pytorch-image-models into jameslahm-main
2023-10-20 11:08:12 -07:00
d3ebdcfd93
Disable strict load when siglip vit pooling removed
2023-10-19 12:03:40 -07:00
e728f3efdb
Cleanup ijepa models, they're just gap (global-avg-pool) models w/o heads. fc-norm conversion was wrong, gigantic should have been giant
2023-10-17 15:44:46 -07:00
49a459e8f1
Merge remote-tracking branch 'upstream/main' into vit_siglip_and_reg
2023-10-17 09:36:48 -07:00
a58f9162d7
Missed __init__.py update for attention pooling layer add
2023-10-17 09:28:21 -07:00
59b622233b
Change ijepa names, add pretrain cfg for reg experimentts
2023-10-17 07:16:17 -07:00
71365165a2
Add SigLIP weights
2023-10-16 23:26:08 -07:00
42daa3b497
Add full set of SigLIP models
2023-10-10 22:15:45 -07:00
4aa166de9c
Add hgnet ssld weights
2023-10-09 19:14:10 +08:00
159e91605c
Add PP-HGNet and PP-HGNetv2 models
2023-10-09 19:04:58 +08:00
7ce65a83a2
Removing unused self.drop
2023-10-05 11:20:57 -07:00
884ef88818
fix all SDPA dropouts
2023-10-05 08:58:41 -07:00
b500cae4c5
fastvit: don't dropout in eval
2023-10-05 08:58:41 -07:00
b9dde58076
Fixup attention pooling in siglip vit support
2023-10-02 11:44:12 -07:00
f061b539d7
Update RepViT models
2023-10-01 14:00:53 +08:00
99cfd6702f
Use global pool arg to select attention pooling in head
2023-09-30 16:16:21 -07:00
82cc53237e
Working on support for siglip (w/ attn pool) vit backbone, and adding registers (reg tokens)
2023-09-30 16:03:01 -07:00
054c763fca
Bump to dev 0.9.8 version
2023-09-27 10:27:47 -07:00
6bae514656
Add pretrained patch embed resizing to swin
2023-09-27 10:27:28 -07:00
5c504b4ded
flip these two
2023-09-27 10:24:12 -07:00
8ba2038e6b
fast_vit: propagate act_layer argument
2023-09-27 10:24:12 -07:00
95ba90157f
Update tiny_vit.py to fix bug
2023-09-23 10:05:52 -07:00
245ad4f41a
Added missing RuntimeError to builder functions of models that do not currently support feature extraction
2023-09-19 08:19:14 -07:00
d4c21b95f4
Update repghost.py
2023-09-15 11:41:56 -07:00
7eb7d13845
Fix in_features for linear layer in reset_classifier.
2023-09-13 09:29:38 -07:00
34ae2861f4
Version 0.9.7
2023-09-01 15:06:55 -07:00
0d124ffd4f
Update README. Fine-grained layer-wise lr decay working for tiny_vit and both efficientvits. Minor fixes.
2023-09-01 15:05:29 -07:00
2f0fbb59b3
TinyViT weights on HF hub
2023-09-01 11:05:56 -07:00
507cb08acf
TinyVitBlock needs adding as leaf for FX now, tweak a few dim names
2023-09-01 11:05:56 -07:00
9caf32b93f
Move levit style pos bias resize with other rel pos bias utils
2023-09-01 11:05:56 -07:00
63417b438f
TinyViT adjustments
...
* keep most of net in BCHW layout, performance appears same, can remove static resolution attribs and features easier to use
* add F.sdpa, decent gains in pt 2.1
* tweak crop pct based on eval
2023-09-01 11:05:56 -07:00
39aa44b192
Fixing tinyvit trace issue
2023-09-01 11:05:56 -07:00
aea3b9c854
Fixing tinyvit input_size issue
2023-09-01 11:05:56 -07:00
fabc4e5bcd
Fixing tinyvit torchscript issue
2023-09-01 11:05:56 -07:00
bae949f830
fix attention_bias_cache in tinyvit
2023-09-01 11:05:56 -07:00
170a5b6e27
add tinyvit
2023-09-01 11:05:56 -07:00
983310d6a2
Fix #1935 , torch.amp.autocast -> torch.autocast (namespace issue for 1.10 pt compat)
2023-08-30 15:03:28 -07:00
f544d4916c
Version 0.9.6 for release
2023-08-29 09:14:13 -07:00
Ross Wightman
Ross Wightman
fzyzcjy
fzyzcjy
Thien Tran
Cheng-Ling Lai
SmilingWolf
Li zhuoqun
kalazus
方曦
SeeFun
LR
Fredo Guan
akiyuki ishikawa
Dillon Laird
Laureηt
LittleNyima
a-r-r-o-w
Laureηt
Patrick Labatut
mjamroz
Tush9905
pUmpKin-Co
lucapericlp
Yassine
jameslahm
Nguyen Nhat Hoang
belfner
Thorsten Hempel