a8e34051c1
Unbreak gamma remap impacting beit checkpoint load, version bump to 0.6.4
2022-07-07 23:07:43 -07:00
7d4b3807d5
Support DeiT-3 (Revenge of the ViT) checkpoints. Add non-overlapping (w/ class token) pos-embed support to vit.
2022-07-04 22:25:22 -07:00
7d657d2ef4
Improve resolve_pretrained_cfg behaviour when no cfg exists, warn instead of crash. Improve usability ex #1311
2022-06-24 14:55:25 -07:00
f5ca4141f7
Adjust arg order for recent vit model args, add a few comments
2022-05-02 22:41:38 -07:00
41dc49a337
Vision Transformer refactoring and Rel Pos impl
2022-05-02 15:37:39 -07:00
1618527098
Add layer scale and parallel blocks to vision_transformer
2022-03-23 16:09:07 -07:00
0862e6ebae
Fix correctness of some group matching regex (no impact on result), some formatting, missed forward_head for resnet
2022-03-19 14:58:54 -07:00
372ad5fa0d
Significant model refactor and additions:
...
* All models updated with revised foward_features / forward_head interface
* Vision transformer and MLP based models consistently output sequence from forward_features (pooling or token selection considered part of 'head')
* WIP param grouping interface to allow consistent grouping of parameters for layer-wise decay across all model types
* Add gradient checkpointing support to a significant % of models, especially popular architectures
* Formatting and interface consistency improvements across models
* layer-wise LR decay impl part of optimizer factory w/ scale support in scheduler
* Poolformer and Volo architectures added
2022-02-28 13:56:23 -08:00
5f81d4de23
Move DeiT to own file, vit getting crowded. Working towards fixing #1029 , make pooling interface for transformers and mlp closer to convnets. Still working through some details...
2022-01-26 22:53:57 -08:00
95cfc9b3e8
Merge remote-tracking branch 'origin/master' into norm_norm_norm
2022-01-25 22:20:45 -08:00
abc9ba2544
Transitioning default_cfg -> pretrained_cfg. Improving handling of pretrained_cfg source (HF-Hub, files, timm config, etc). Checkpoint handling tweaks.
2022-01-25 21:54:13 -08:00
07379c6d5d
Add vit_base2_patch32_256 for a model between base_patch16 and patch32 with a slightly larger img size and width
2022-01-24 14:46:47 -08:00
010b486590
Add Dino pretrained weights (no head) for vit models. Add support to tests and helpers for models w/ no classifier (num_classes=0 in pretrained cfg)
2022-01-17 12:20:02 -08:00
e967c72875
Update REAMDE.md. Sneak in g/G (giant / gigantic?) ViT defs from scaling paper
2022-01-14 16:28:27 -08:00
656757d26b
Fix MobileNetV2 head conv size for multiplier < 1.0. Add some missing modification copyrights, fix starting date of some old ones.
2022-01-14 16:28:27 -08:00
5220711d87
Added B/8 models to ViT.
2021-11-14 11:01:48 +00:00
f805ba86d9
use .unbind instead of explicitly listing the indices
2021-10-24 21:08:47 +02:00
78933122c9
Fix silly typo
2021-08-27 09:22:20 -07:00
708d87a813
Fix ViT SAM weight compat as weights at URL changed to not use repr layer. Fix #825 . Tweak optim test.
2021-08-27 09:20:13 -07:00
20b2d4b69d
Use bicubic interpolation in resize_pos_embed()
2021-07-12 10:38:31 -07:00
6d8272e92c
Add SAM pretrained model defs/weights for ViT B16 and B32 models.
2021-07-08 11:51:12 -07:00
85f894e03d
Fix ViT in21k representation (pre_logits) layer handling across old and new npz checkpoints
2021-06-23 10:38:34 -07:00
b41cffaa93
Fix a few issues loading pretrained vit/bit npz weights w/ num_classes=0 __init__ arg. Missed a few other small classifier handling detail on Mlp, GhostNet, Levit. Should fix #713
2021-06-22 23:16:05 -07:00
9c9755a808
AugReg release
2021-06-20 17:46:06 -07:00
b319eb5b5d
Update ViT weights, more details to be added before merge.
2021-06-18 16:16:49 -07:00
b9cfb64412
Support npz custom load for vision transformer hybrid models. Add posembed rescale for npz load.
2021-06-14 12:31:44 -07:00
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
2021-06-12 16:40:02 -07:00
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.
2021-05-24 21:13:26 -07:00
30b9880d06
Minor adjustment, mutable default arg, extra check of valid len...
2021-05-21 17:20:51 -07:00
8086943b6f
allow resize positional embeddings to non-square grid
2021-05-20 11:27:58 +01:00
b2c305c2aa
Move Mlp and PatchEmbed modules into layers. Being used in lots of models now...
2021-05-06 14:03:23 -07:00
a0492e3b48
A few miil weights naming tweaks to improve compat with model registry and filtering wildcards.
2021-04-28 10:33:02 -07:00
19e1b67a84
old spaces
2021-04-28 09:01:29 +03:00
a443865876
update naming and scores
2021-04-28 08:57:06 +03:00
cf0e371594
84_0
2021-04-27 22:33:55 +03:00
0968bdeca3
vit, tresnet and mobilenetV3 ImageNet-21K-P weights
2021-04-27 20:54:06 +03:00
f606c45c38
Add Swin Transformer models from https://github.com/microsoft/Swin-Transformer
2021-04-13 12:17:21 -07:00
bf2ca6bdf4
Merge jax and original weight init
2021-04-01 18:11:51 -07:00
acbd698c83
Update README.md with updates. Small tweak to head_dist handling.
2021-04-01 17:49:05 -07:00
288682796f
Update benchmark script to add precision arg. Fix some downstream (DeiT) compat issues with latest changes. Bump version to 0.4.7
2021-04-01 16:40:12 -07:00
ea9c9550b2
Fully move ViT hybrids to their own file, including embedding module. Remove some extra DeiT models that were for benchmarking only.
2021-04-01 14:17:38 -07:00
a5310a3451
Merge remote-tracking branch 'origin/benchmark-fixes-vit_hybrids' into pit_and_vit_update
2021-04-01 12:15:34 -07:00
7953e5d11a
Fix pos_embed scaling for ViT and num_classes != 1000 for pretrained distilled deit and pit models. Fix #426 and fix #433
2021-03-31 23:11:28 -07:00
a760a4c3f4
Some ViT cleanup, merge distilled model with main, fixup torchscript support for distilled models
2021-03-31 18:21:02 -07:00
cf5fec5047
Cleanup experimental vit weight init a bit
2021-03-20 09:44:24 -07:00
cbcb76d72c
Should have included Conv2d layers in original weight init. Lets see what the impact is...
2021-03-18 23:15:48 -07:00
4de57ccf01
Add weight init scheme that's closer to JAX impl
2021-03-18 15:35:22 -07:00
45c048ba13
A few minor fixes and bit more cleanup on the huggingface hub integration.
2021-03-17 13:18:52 -07:00
d584e7f617
Support for huggingface hub via create_model and default_cfgs.
...
* improve consistency of model creation helper fns
* add comments to some of the model helpers
* support passing external default_cfgs so they can be sourced from hub
2021-03-16 22:48:26 -07:00
17cdee7354
Fix C&P patch_size error, and order of op patch_size arg resolution bug. Remove a test vit model.
2021-03-01 16:53:32 -08:00
Ross Wightman
Martins Bruveris
Thomas Viehmann
Ying Jin
Alexander Soare
talrid