Ross Wightman
4027412757
Add resnet33ts weights, update resnext26ts baseline weights
2021-09-09 14:46:41 -07:00
Richard Chen
9fe5798bee
fix bug for reset classifier and fix for validating the dimension
2021-09-08 21:58:17 -04:00
Richard Chen
3718c5a5bd
fix loading pretrained model
2021-09-08 11:53:05 -04:00
Richard Chen
bb50b69a57
fix for torch script
2021-09-08 11:20:59 -04:00
nateraw
abf9d51bc3
🚧 wip
2021-09-07 18:39:26 -06:00
Ross Wightman
5bd04714e4
Cleanup weight init for byob/byoanet and related
2021-09-05 15:34:05 -07:00
Ross Wightman
8642401e88
Swap botnet 26/50 weights/models after realizing a mistake in arch def, now figuring out why they were so low...
2021-09-05 15:17:19 -07:00
Ross Wightman
5f12de4875
Add initial AttentionPool2d that's being trialed. Fix comment and still trying to improve reliability of sgd test.
2021-09-05 12:41:14 -07:00
Ross Wightman
76881d207b
Add baseline resnet26t @ 256x256 weights. Add 33ts variant of halonet with at least one halo in stage 2,3,4
2021-09-04 14:52:54 -07:00
Ross Wightman
484e61648d
Adding the attn series weights, tweaking model names, comments...
2021-09-03 18:09:42 -07:00
nateraw
28d2841acf
💄 apply isort
2021-09-01 18:15:08 -06:00
Ross Wightman
492c0a4e20
Update HaloAttn comment
2021-09-01 17:14:31 -07:00
nateraw
e72c989973
✨ add ability to push to hf hub
2021-09-01 18:14:28 -06:00
Richard Chen
7ab9d4555c
add crossvit
2021-09-01 17:13:12 -04:00
Ross Wightman
3b9032ea48
Use Tensor.unfold().unfold() for HaloAttn, fast like as_strided but more clarity
2021-08-27 12:45:53 -07:00
Ross Wightman
78933122c9
Fix silly typo
2021-08-27 09:22:20 -07:00
Ross Wightman
2568ffc5ef
Merge branch 'master' into attn_update
2021-08-27 09:21:22 -07:00
Ross Wightman
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
Ross Wightman
8449ba210c
Improve performance of HaloAttn, change default dim calc. Some cleanup / fixes for byoanet. Rename resnet26ts to tfs to distinguish (extra fc).
2021-08-26 21:56:44 -07:00
Ross Wightman
a8b65695f1
Add resnet26ts and resnext26ts models for non-attn baselines
2021-08-21 12:42:10 -07:00
Ross Wightman
a5a542f17d
Fix typo
2021-08-20 17:47:23 -07:00
Ross Wightman
925e102982
Update attention / self-attn based models from a series of experiments:
...
* remove dud attention, involution + my swin attention adaptation don't seem worth keeping
* add or update several new 26/50 layer ResNe(X)t variants that were used in experiments
* remove models associated with dead-end or uninteresting experiment results
* weights coming soon...
2021-08-20 16:13:11 -07:00
Ross Wightman
01cb46a9a5
Add gc_efficientnetv2_rw_t weights (global context instead of SE attn). Add TF XL weights even though the fine-tuned ones don't validate that well. Change default arg for GlobalContext to use scal (mul) mode.
2021-08-07 16:45:29 -07:00
Ross Wightman
d3f7440650
Add EfficientNetV2 XL model defs
2021-07-22 13:15:24 -07:00
Ross Wightman
72b227dcf5
Merge pull request #750 from drjinying/master
...
Specify "interpolation" mode in vision_transformer's resize_pos_embed
2021-07-13 11:01:20 -07:00
Ross Wightman
748ab852ca
Allow act_layer switch for xcit, fix in_chans for some variants
2021-07-12 13:27:29 -07:00
Ying Jin
20b2d4b69d
Use bicubic interpolation in resize_pos_embed()
2021-07-12 10:38:31 -07:00
Ross Wightman
d3255adf8e
Merge branch 'xcit' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-xcit
2021-07-12 08:30:30 -07:00
Ross Wightman
f8039c7492
Fix gc effv2 model cfg name
2021-07-11 12:14:31 -07:00
Alexander Soare
3a55a30ed1
add notes from author
2021-07-11 14:25:58 +01:00
Alexander Soare
899cf84ccc
bug fix - missing _dist postfix for many of the 224_dist models
2021-07-11 12:41:51 +01:00
Alexander Soare
623e8b8eb8
wip xcit
2021-07-11 09:39:38 +01:00
Ross Wightman
392368e210
Add efficientnetv2_rw_t defs w/ weights, and gc variant, as well as gcresnet26ts for experiments. Version 0.4.13
2021-07-09 16:46:52 -07:00
Ross Wightman
6d8272e92c
Add SAM pretrained model defs/weights for ViT B16 and B32 models.
2021-07-08 11:51:12 -07:00
Ross Wightman
ee4d8fc69a
Remove unecessary line from nest post refactor
2021-07-05 21:22:46 -07:00
Ross Wightman
8165cacd82
Realized LayerNorm2d won't work in all cases as is, fixed.
2021-07-05 18:21:34 -07:00
Ross Wightman
81cd6863c8
Move aggregation (convpool) for nest into NestLevel, cleanup and enable features_only use. Finalize weight url.
2021-07-05 18:20:49 -07:00
Ross Wightman
6ae0ac6420
Merge branch 'nested_transformer' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-nested_transformer
2021-07-03 12:45:26 -07:00
Alexander Soare
7b8a0017f1
wip to review
2021-07-03 12:10:12 +01:00
Alexander Soare
b11d949a06
wip checkpoint with some feature extraction work
2021-07-03 11:45:19 +01:00
Alexander Soare
23bb72ce5e
nested_transformer wip
2021-07-02 20:12:29 +01:00
Ross Wightman
766b4d3262
Fix features for resnetv2_50t
2021-06-28 15:56:24 -07:00
Ross Wightman
e8045e712f
Fix BatchNorm for ResNetV2 non GN models, add more ResNetV2 model defs for future experimentation, fix zero_init of last residual for pre-act.
2021-06-28 10:52:45 -07:00
Ross Wightman
20a2be14c3
Add gMLP-S weights, 79.6 top-1
2021-06-23 10:40:30 -07:00
Ross Wightman
85f894e03d
Fix ViT in21k representation (pre_logits) layer handling across old and new npz checkpoints
2021-06-23 10:38:34 -07:00
Ross Wightman
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
Ross Wightman
9c9755a808
AugReg release
2021-06-20 17:46:06 -07:00
Ross Wightman
381b279785
Add hybrid model fwds back
2021-06-19 22:28:44 -07:00
Ross Wightman
26f04a8e3e
Fix a weight link
2021-06-19 16:39:36 -07:00
Ross Wightman
8f4a0222ed
Add GMixer-24 MLP model weights, trained w/ TPU + PyTorch XLA
2021-06-18 16:49:28 -07:00
