mirrors
/
pytorch-image-models
mirror of https://github.com/huggingface/pytorch-image-models.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
1,996 Commits
136 Branches
65 Tags
47 MiB
Commit Graph

1996 Commits (ea3519a5f0c2f249b1d650a3750c3c9d13c266ce)
 

Author SHA1 Message Date
Ross Wightman ea3519a5f0 Fix dynamic_resize for deit models (distilled or no_embed_cls) and vit w/o class tokens 2023-08-27 15:58:35 -07:00
Ross Wightman 4d8ecde6cc Fix torchscript for vit-hybrid dynamic_resize 2023-08-27 15:58:35 -07:00
Ross Wightman fdd8c7c2da Initial impl of dynamic resize for existing vit models (incl vit-resnet hybrids) 2023-08-27 15:58:35 -07:00
Ross Wightman 38c474e3de Update README, add --reparm to onnx_export 2023-08-25 11:04:34 -07:00
Ross Wightman 5d599a6a10 RepViT weights on HF hub 2023-08-25 10:39:02 -07:00
Ross Wightman 56c285445c Wrong pool size for 384x384 inception_next_base 2023-08-24 18:31:44 -07:00
Ross Wightman af9f56f3bf inception_next dilation support, weights on hf hub, classifier reset / global pool / no head fixes 2023-08-24 18:31:44 -07:00
Ross Wightman 2d33b9df6c Add features_only support to inception_next 2023-08-24 18:31:44 -07:00
Ross Wightman 3d8d7450ad InceptionNeXt using timm builder, more cleanup 2023-08-24 18:31:44 -07:00
Ross Wightman f4cf9775c3 Adding InceptionNeXt 2023-08-24 18:31:44 -07:00
Ross Wightman d2e3c09ce1
Update version.py 2023-08-23 22:51:56 -07:00
Ross Wightman d6c348765a Fix first_conv for mobileone and fastvit 2023-08-23 22:50:37 -07:00
Ross Wightman 16334e4bec Fix two fastvit issues 2023-08-23 22:50:37 -07:00
Ross Wightman 5242ba6edc MobileOne and FastViT weights on HF hub, more code cleanup and tweaks, features_only working. Add reparam flag to validate and benchmark, support reparm of all models with fuse(), reparameterize() or switch_to_deploy() methods on modules 2023-08-23 22:50:37 -07:00
Ross Wightman 40dbaafef5 Stagify FastViT /w downsample to top of stage 2023-08-23 22:50:37 -07:00
Ross Wightman 8470eb1cb5 More fastvit & mobileone updates, ready for weight upload 2023-08-23 22:50:37 -07:00
Ross Wightman 8474508d07 More work on FastViT, use own impl of MobileOne, validation working with remapped weight, more refactor TODO 2023-08-23 22:50:37 -07:00
Ross Wightman c7a20cec13 Begin adding FastViT 2023-08-23 22:50:37 -07:00
Ross Wightman 7fd3674d0d Add mobileone and update repvgg 2023-08-23 22:50:37 -07:00
Ross Wightman 3055411c1b
Fix samvit bug, add F.sdpa support and ROPE option (#1920) 
* Fix a bug I introduced in samvit, add F.sdpa support and ROPE option to samvit, neck is LayerNorm if not used and standard classifier used

* Add attn dropout to F.sdpa

* Fix fx trace for sam vit

* Fixing torchscript issues in samvit

* Another torchscript fix

* samvit head fc name fix
 2023-08-20 21:22:59 -07:00
Ross Wightman 300f54a96f Another effcientvit (mit) tweak, fix torchscript/fx conflict with autocast disable 2023-08-20 15:07:25 -07:00
Ross Wightman dc18cda2e7 efficientvit (mit) msa attention q/k/v ops need to be in float32 to train w/o NaN 2023-08-20 11:49:36 -07:00
Ross Wightman e6aeb91ac1
Merge pull request #1923 from huggingface/yehuitang-Add-GhostNetV2 
ghostnetv2 cleanup
 2023-08-20 02:27:58 -07:00
Ross Wightman be4e0d8f76 Update attrib comment to include v2 2023-08-19 23:39:09 -07:00
Ross Wightman 126a58e563 Combine ghostnetv2 with ghostnet, reduec redundancy, add weights to hf hub. 2023-08-19 23:33:43 -07:00
Ross Wightman 3f320a9e57 Merge branch 'Add-GhostNetV2' of github.com:yehuitang/pytorch-image-models into yehuitang-Add-GhostNetV2 2023-08-19 22:07:54 -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
Ross Wightman 69e0ca2e36 Weights on hf hub, bicubic yields slightly better eval 2023-08-19 16:25:45 -07:00
Ross Wightman b8011565bd
Merge pull request #1894 from seefun/master 
add two different EfficientViT models
 2023-08-19 09:24:14 -07:00
Ross Wightman 7d7589e8da Fixing efficient_vit torchscript, fx, default_cfg issues 2023-08-18 23:23:11 -07:00
Ross Wightman 58ea1c02c4 Add fixed_input_size flag to msra efficient_vit 2023-08-18 16:48:17 -07:00
Ross Wightman c28324a150 Update efficient_vit (msra), hf hub weights 2023-08-18 16:45:37 -07:00
Ross Wightman e700a32626 Cleanup of efficient_vit (mit), tweak eps for better AMP behaviour, formatting/cleanup, weights on hf hub 2023-08-18 16:06:07 -07:00
方曦 00f670fa69 fix bug in ci for efficientvits 2023-08-17 14:40:17 +08:00
Chengpeng Chen e7f97cb5ce Fix typos RepGhost models 2023-08-16 14:27:45 +08:00
Chengpeng Chen d1d0193615 Add RepGhost models and weights 2023-08-16 11:54:53 +08:00
Ross Wightman 24fc720d34
Merge pull request #1918 from Mingosnake/fix-efficientformerv2-typo 
Fix typo in efficientformer_v2
 2023-08-15 20:04:35 -07:00
Minseo Kang 7938f28542 Fix typo in efficientformer_v2 2023-08-16 03:29:01 +09:00
yehuitang e4babe7372
Add GhostNetV2 2023-08-13 18:23:52 +08:00
yehuitang b407794e3a
Add GhostNetV2 2023-08-13 18:20:27 +08:00
yehuitang fc865282e5
Add ghostnetv2.py 2023-08-13 18:16:26 +08:00
Ross Wightman da75cdd212
Merge pull request #1900 from huggingface/swin_maxvit_resize 
Add support for resizing swin transformer, maxvit, coatnet at creation time
 2023-08-11 15:05:28 -07:00
Ross Wightman 78a04a0e7d
Merge pull request #1911 from dsuess/1910-fixes-batchnormact-fx 
Register norm_act layers as leaf modules
 2023-08-11 14:34:16 -07:00
Ross Wightman 379998ed5d
Merge pull request #1914 from developer0hye/developer0hye-patch-1 
Set self.num_features to neck_chans if neck_chans > 0 for vision_transformer_sam
 2023-08-11 11:23:57 -07:00
Yonghye Kwon 2048f6f20f
set self.num_features to neck_chans if neck_chans > 0 2023-08-11 13:45:06 +09:00
Ross Wightman 3a44e6c602 Fix #1912 CoaT model not loading w/ return_interm_layers 2023-08-10 11:15:58 -07:00
Daniel Suess 986de90360
Register orm_act layers as leaf modules 2023-08-10 15:37:26 +10:00
Ross Wightman c692715388 Some RepVit tweaks 
* add head dropout to RepVit as all models have that arg
* default train to non-distilled head output via distilled_training flag (set_distilled_training) so fine-tune works by default w/o distillation script
* camel case naming tweaks to match other models
 2023-08-09 12:41:12 -07:00
Ross Wightman c153cd4a3e Add more advanced interpolation method from BEiT and support non-square window & image size adaptation for 
* beit/beit-v2
* maxxvit/coatnet
* swin transformer
And non-square windows for swin-v2
 2023-08-08 16:41:16 -07:00
Ross Wightman f6771909ff
Merge pull request #1903 from twmht/fix_num_classes 
fix num_classes not found in repvit
 2023-08-07 16:35:36 -07:00