You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Aman Arora 40c506ba1e Add ConViT		3 years ago
..
layers	Add preliminary gMLP and ResMLP impl to Mlp-Mixer	3 years ago
pruned	…
__init__.py	Add ConViT	3 years ago
byoanet.py	More adjustments to ByoaNet models for further experiments.	3 years ago
byobnet.py	Update ByoaNet comments. Fix first Steam feat chs for ByobNet.	4 years ago
cait.py	Fix crop_pct for cait models.	3 years ago
coat.py	Rethink name of patch embed grid info	3 years ago
convit.py	Add ConViT	3 years ago
cspnet.py	…
densenet.py	…
dla.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
dpn.py	…
efficientnet.py	Change 21k model naming from _21k to _in21k for consistency with existing 21k models.	3 years ago
efficientnet_blocks.py	EfficientNetV2 official impl w/ weights ported from TF. Cleanup/refactor of related EfficientNet classes and models.	3 years ago
efficientnet_builder.py	EfficientNetV2 official impl w/ weights ported from TF. Cleanup/refactor of related EfficientNet classes and models.	3 years ago
factory.py	…
features.py	…
ghostnet.py	EfficientNetV2 official impl w/ weights ported from TF. Cleanup/refactor of related EfficientNet classes and models.	3 years ago
gluon_resnet.py	…
gluon_xception.py	…
hardcorenas.py	EfficientNetV2 official impl w/ weights ported from TF. Cleanup/refactor of related EfficientNet classes and models.	3 years ago
helpers.py	Fix pos_embed scaling for ViT and num_classes != 1000 for pretrained distilled deit and pit models. Fix #426 and fix #433	4 years ago
hrnet.py	…
hub.py	…
inception_resnet_v2.py	…
inception_v3.py	…
inception_v4.py	…
mlp_mixer.py	mixer_b16_224_miil, mixer_b16_224_miil_in21k models	3 years ago
mobilenetv3.py	EfficientNetV2 official impl w/ weights ported from TF. Cleanup/refactor of related EfficientNet classes and models.	3 years ago
nasnet.py	…
nfnet.py	Add prelim efficientnet_v2s weights from 224x224 train, eval 83.3 @ 288. Add eca_nfnet_l1 weights, train at 256, eval 84 @ 320.	4 years ago
pit.py	Add Swin Transformer models from https://github.com/microsoft/Swin-Transformer	4 years ago
pnasnet.py	…
registry.py	Add default_cfg options for min_input_size / fixed_input_size, queries in model registry, and use for testing self-attn models	4 years ago
regnet.py	Add regnety_160 weights from DeiT teacher model, update that and my regnety_032 weights to use higher test size.	4 years ago
res2net.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
resnest.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
resnet.py	Move Mlp and PatchEmbed modules into layers. Being used in lots of models now...	3 years ago
resnetv2.py	Fix ResNetV2 pretrained classifier issue. Fixes #540	4 years ago
rexnet.py	…
selecsls.py	…
senet.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
sknet.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
swin_transformer.py	Rethink name of patch embed grid info	3 years ago
tnt.py	Move Mlp and PatchEmbed modules into layers. Being used in lots of models now...	3 years ago
tresnet.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
vgg.py	…
vision_transformer.py	Move Mlp and PatchEmbed modules into layers. Being used in lots of models now...	3 years ago
vision_transformer_hybrid.py	Update benchmark script to add precision arg. Fix some downstream (DeiT) compat issues with latest changes. Bump version to 0.4.7	4 years ago
vovnet.py	…
xception.py	…
xception_aligned.py	…