pytorch-image-models

History

Ross Wightman 3785c234d7 Remove clip vit models that won't be ft and comment two that aren't uploaded yet		2 years ago
..
layers	MaxVit, ViT, ConvNeXt, and EfficientNet-v2 updates	2 years ago
pruned	…
__init__.py	Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses	2 years ago
beit.py	BEiT-V2 checkpoints didn't remove 'module' from weights, adapt checkpoint filter	2 years ago
byoanet.py	…
byobnet.py	…
cait.py	Remove some redundant requires_grad=True from nn.Parameter in third party code	2 years ago
coat.py	…
convit.py	…
convmixer.py	…
convnext.py	Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses	2 years ago
crossvit.py	…
cspnet.py	Add weights for two 'Edge' block (3x3->1x1) variants of CS3 networks.	2 years ago
deit.py	Add DeiT-III 'medium' model defs and weights	2 years ago
densenet.py	Fix two default args in DenseNet blocks... fix #1427	2 years ago
dla.py	Fix type in dla weight update	2 years ago
dpn.py	…
edgenext.py	Add edgenext_base model def & weight link, update to improve ONNX export #1385	2 years ago
efficientformer.py	More test fixes, pool size for 256x256 maxvit models	2 years ago
efficientnet.py	MaxVit, ViT, ConvNeXt, and EfficientNet-v2 updates	2 years ago
efficientnet_blocks.py	…
efficientnet_builder.py	…
factory.py	Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses	2 years ago
features.py	…
fx_features.py	Update type hint for `register_notrace_module`	2 years ago
gcvit.py	Make gcvit window size ratio based to improve resolution changing support #1449 . Change default init to original.	2 years ago
ghostnet.py	…
gluon_resnet.py	…
gluon_xception.py	…
hardcorenas.py	Update a bunch of weights with external links to timm release assets. Fixes issue with *aliyuncs.com returning forbidden. Did pickle scan / verify and re-hash. Add TresNet-V2-L weights.	2 years ago
helpers.py	Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses	2 years ago
hrnet.py	Ensure all model entrypoint fn default to `pretrained=False` (a few didn't)	2 years ago
hub.py	Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses	2 years ago
inception_resnet_v2.py	…
inception_v3.py	Initial multi-weight support, handled so old pretraing config handling co-exists with new tags.	2 years ago
inception_v4.py	…
levit.py	…
maxxvit.py	Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses	2 years ago
mlp_mixer.py	Update a bunch of weights with external links to timm release assets. Fixes issue with *aliyuncs.com returning forbidden. Did pickle scan / verify and re-hash. Add TresNet-V2-L weights.	2 years ago
mobilenetv3.py	Update a bunch of weights with external links to timm release assets. Fixes issue with *aliyuncs.com returning forbidden. Did pickle scan / verify and re-hash. Add TresNet-V2-L weights.	2 years ago
mobilevit.py	Change models with mean 0,0,0 std 1,1,1 from int to float for consistency as mentioned in #1355	2 years ago
mvitv2.py	pretrained_cfg entry for mvitv2_small_cls	2 years ago
nasnet.py	Update a bunch of weights with external links to timm release assets. Fixes issue with *aliyuncs.com returning forbidden. Did pickle scan / verify and re-hash. Add TresNet-V2-L weights.	2 years ago
nest.py	…
nfnet.py	…
pit.py	…
pnasnet.py	…
poolformer.py	Remove some redundant requires_grad=True from nn.Parameter in third party code	2 years ago
pretrained.py	Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses	2 years ago
pvt_v2.py	More model and test fixes	2 years ago
registry.py	Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses	2 years ago
regnet.py	Initial multi-weight support, handled so old pretraing config handling co-exists with new tags.	2 years ago
res2net.py	…
resnest.py	…
resnet.py	Update a bunch of weights with external links to timm release assets. Fixes issue with *aliyuncs.com returning forbidden. Did pickle scan / verify and re-hash. Add TresNet-V2-L weights.	2 years ago
resnetv2.py	Initial multi-weight support, handled so old pretraing config handling co-exists with new tags.	2 years ago
rexnet.py	…
selecsls.py	…
senet.py	Update a bunch of weights with external links to timm release assets. Fixes issue with *aliyuncs.com returning forbidden. Did pickle scan / verify and re-hash. Add TresNet-V2-L weights.	2 years ago
sequencer.py	Fix tests for rank-4 output where feature channels dim is -1 (3) and not 1	3 years ago
sknet.py	…
swin_transformer.py	Update a bunch of weights with external links to timm release assets. Fixes issue with *aliyuncs.com returning forbidden. Did pickle scan / verify and re-hash. Add TresNet-V2-L weights.	2 years ago
swin_transformer_v2.py	Add updated vit_relpos weights, and impl w/ support for official swin-v2 differences for relpos. Add bias control support for MLP layers	3 years ago
swin_transformer_v2_cr.py	Remove persistent buffers from Swin-V2. Change SwinV2Cr cos attn + tau/logit_scale to match official, add ckpt convert, init_value zeros resid LN weight by default	3 years ago
tnt.py	…
tresnet.py	Update tresnet features_info for v2	2 years ago
twins.py	…
vgg.py	…
visformer.py	…
vision_transformer.py	Remove clip vit models that won't be ft and comment two that aren't uploaded yet	2 years ago
vision_transformer_hybrid.py	Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses	2 years ago
vision_transformer_relpos.py	Update vit_relpos w/ some additional weights, some cleanup to match recent vit updates, more MLP log coord experiments.	2 years ago
volo.py	…
vovnet.py	…
xception.py	…
xception_aligned.py	…
xcit.py	Fix typo in PositionalEncodingFourier	2 years ago