mirrors/pytorch-image-models
1
0
Fork 0
mirror of https://github.com/huggingface/pytorch-image-models.git synced 2025-06-03 15:01:08 +08:00
Code Issues Projects Releases Wiki Activity
pytorch-image-models/timm/models
History
Leng Yue 5cc87e6485
Add dinov2 pretrained models (#1797) 
* add dinov2 small, base, and large

* fix input size

* fix swiglu & dinov2 vit giant

* use SwiGLUPacked to replace GluMlp

* clean up & add ffn_layer placeholder for ParallelScalingBlock
2023-05-09 12:24:47 -07:00
..
_pruned
…
layers
…
__init__.py
Metaformer baselines for vision (final PR with cleanup) (#1793)
2023-05-05 11:18:26 -07:00
_builder.py
…
_efficientnet_blocks.py
…
_efficientnet_builder.py
…
_factory.py
Small factory handling fix for pretrained tag vs cfg
2023-04-11 07:42:13 -07:00
_features_fx.py
…
_features.py
…
_helpers.py
…
_hub.py
More models w/ multi-weight support, moving to HF hub. Removing inplace_abn from all models including TResNet
2023-04-20 22:44:49 -07:00
_manipulate.py
…
_pretrained.py
…
_prune.py
…
_registry.py
Update warning message for deprecated model names
2023-04-05 17:24:17 -07:00
beit.py
fast_attn -> fused_attn, implement global config for enable/disable fused_attn, add to more models. vit clip openai 336 weights.
2023-04-10 12:04:33 -07:00
byoanet.py
More models w/ multi-weight support, moving to HF hub. Removing inplace_abn from all models including TResNet
2023-04-20 22:44:49 -07:00
byobnet.py
Add update byobnet.py w/ models pushed to HF hub
2023-03-22 10:00:00 -07:00
cait.py
cait, volo, xvit hub weights
2023-04-14 10:13:13 -07:00
coat.py
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
convit.py
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
convmixer.py
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
convnext.py
Add ImageNet-12k intermediate fine-tunes of convnext base & large CLIP models, add first 1k fine-tune of xxlarge
2023-03-31 16:45:01 -07:00
crossvit.py
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
cspnet.py
cspnet models on HF hub w/ multi-weight support
2023-04-12 14:02:38 -07:00
davit.py
fast_attn -> fused_attn, implement global config for enable/disable fused_attn, add to more models. vit clip openai 336 weights.
2023-04-10 12:04:33 -07:00
deit.py
Improve kwarg passthrough for swin, vit, deit, beit, eva
2023-04-05 21:37:16 -07:00
densenet.py
DenseNet, DPN, VoVNet, Aligned Xception weights on HF hub. DenseNet grad_checkpointing using timm API
2023-04-21 16:56:44 -07:00
dla.py
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
dpn.py
DenseNet, DPN, VoVNet, Aligned Xception weights on HF hub. DenseNet grad_checkpointing using timm API
2023-04-21 16:56:44 -07:00
edgenext.py
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
efficientformer_v2.py
Implement patch dropout for eva / vision_transformer, refactor / improve consistency of dropout args across all vit based models
2023-04-07 20:27:23 -07:00
efficientformer.py
Implement patch dropout for eva / vision_transformer, refactor / improve consistency of dropout args across all vit based models
2023-04-07 20:27:23 -07:00
efficientnet.py
Some fixes
2023-04-26 17:46:20 -07:00
eva.py
Add finalized eva CLIP weights pointing to remapped timm hub models
2023-04-10 23:13:12 -07:00
factory.py
…
features.py
…
focalnet.py
Implement patch dropout for eva / vision_transformer, refactor / improve consistency of dropout args across all vit based models
2023-04-07 20:27:23 -07:00
fx_features.py
…
gcvit.py
…
ghostnet.py
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
hardcorenas.py
hardcore nas weights on hf hub
2023-04-21 14:35:10 -07:00
helpers.py
…
hrnet.py
Some fixes
2023-04-26 17:46:20 -07:00
hub.py
…
inception_resnet_v2.py
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
inception_v3.py
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
inception_v4.py
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
levit.py
…
maxxvit.py
fast_attn -> fused_attn, implement global config for enable/disable fused_attn, add to more models. vit clip openai 336 weights.
2023-04-10 12:04:33 -07:00
metaformer.py
Metaformer baselines for vision (final PR with cleanup) (#1793)
2023-05-05 11:18:26 -07:00
mlp_mixer.py
Implement patch dropout for eva / vision_transformer, refactor / improve consistency of dropout args across all vit based models
2023-04-07 20:27:23 -07:00
mobilenetv3.py
…
mobilevit.py
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
mvitv2.py
Implement patch dropout for eva / vision_transformer, refactor / improve consistency of dropout args across all vit based models
2023-04-07 20:27:23 -07:00
nasnet.py
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
nest.py
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
nfnet.py
Fix last min torchscript regression in nfnet changes
2023-03-24 00:10:17 -07:00
pit.py
Fix pit regression
2023-04-26 23:16:06 -07:00
pnasnet.py
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
pvt_v2.py
Always some torchscript issues
2023-04-26 20:42:34 -07:00
registry.py
…
regnet.py
…
res2net.py
Some fixes
2023-04-26 17:46:20 -07:00
resnest.py
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
resnet.py
Wrong pool_size for 288 ft
2023-04-05 16:07:51 -07:00
resnetv2.py
Update resnetv2.py for multi-weight and HF hub weights
2023-03-22 15:38:04 -07:00
rexnet.py
Update crop settings for new rexnet weights
2023-03-22 15:39:49 -07:00
selecsls.py
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
senet.py
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
sequencer.py
Some fixes
2023-04-26 17:46:20 -07:00
sknet.py
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
swin_transformer_v2_cr.py
Implement patch dropout for eva / vision_transformer, refactor / improve consistency of dropout args across all vit based models
2023-04-07 20:27:23 -07:00
swin_transformer_v2.py
Update swin_v2 attn_mask buffer change in #1790 to apply to updated checkpoints in hub
2023-04-11 14:40:32 -07:00
swin_transformer.py
fast_attn -> fused_attn, implement global config for enable/disable fused_attn, add to more models. vit clip openai 336 weights.
2023-04-10 12:04:33 -07:00
tnt.py
Implement patch dropout for eva / vision_transformer, refactor / improve consistency of dropout args across all vit based models
2023-04-07 20:27:23 -07:00
tresnet.py
TResNet weights now on HF hub, modified to remove InplaceABN dependency
2023-04-21 14:20:48 -07:00
twins.py
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
vgg.py
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
visformer.py
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
vision_transformer_hybrid.py
Improve kwarg passthrough for swin, vit, deit, beit, eva
2023-04-05 21:37:16 -07:00
vision_transformer_relpos.py
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
vision_transformer.py
Add dinov2 pretrained models (#1797)
2023-05-09 12:24:47 -07:00
volo.py
cait, volo, xvit hub weights
2023-04-14 10:13:13 -07:00
vovnet.py
DenseNet, DPN, VoVNet, Aligned Xception weights on HF hub. DenseNet grad_checkpointing using timm API
2023-04-21 16:56:44 -07:00
xception_aligned.py
DenseNet, DPN, VoVNet, Aligned Xception weights on HF hub. DenseNet grad_checkpointing using timm API
2023-04-21 16:56:44 -07:00
xception.py
Some fixes
2023-04-26 17:46:20 -07:00
xcit.py
cait, volo, xvit hub weights
2023-04-14 10:13:13 -07:00