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.

Ross Wightman 05313940e2 Add cs3darknet_x, cs3sedarknet_l, and darknetaa53 weights from TPU sessions. Move SE btwn conv1 & conv2 in DarkBlock. Improve SE/attn handling in Csp/DarkNet. Fix leaky_relu bug on older csp models.		2 years ago
..
layers	Add --use-train-size flag to force use of train input_size (over test input size) for validation. Default test-time pooling to use train input size (fixes issues).	2 years ago
pruned	…
__init__.py	Add initial EdgeNeXt import. Significant cleanup / reorg (like ConvNeXt). Fix #1320	2 years ago
beit.py	…
byoanet.py	…
byobnet.py	…
cait.py	…
coat.py	…
convit.py	…
convmixer.py	…
convnext.py	Remove experimental downsample in block support in ConvNeXt. Experiment further before keeping it in.	2 years ago
crossvit.py	…
cspnet.py	Add cs3darknet_x, cs3sedarknet_l, and darknetaa53 weights from TPU sessions. Move SE btwn conv1 & conv2 in DarkBlock. Improve SE/attn handling in Csp/DarkNet. Fix leaky_relu bug on older csp models.	2 years ago
deit.py	Unbreak gamma remap impacting beit checkpoint load, version bump to 0.6.4	2 years ago
densenet.py	…
dla.py	…
dpn.py	…
edgenext.py	x and xx small edgenext models do benefit from larger test input size	2 years ago
efficientnet.py	…
efficientnet_blocks.py	…
efficientnet_builder.py	…
factory.py	…
features.py	…
fx_features.py	…
ghostnet.py	…
gluon_resnet.py	…
gluon_xception.py	…
hardcorenas.py	…
helpers.py	no longer a point using kwargs for pretrain_cfg resolve, just pass explicit arg	2 years ago
hrnet.py	…
hub.py	👽 use hf_hub_download instead of cached_download	2 years ago
inception_resnet_v2.py	…
inception_v3.py	Improve resolve_pretrained_cfg behaviour when no cfg exists, warn instead of crash. Improve usability ex #1311	2 years ago
inception_v4.py	…
levit.py	…
mlp_mixer.py	…
mobilenetv3.py	…
mobilevit.py	Add MobileVitV2 support. Fix #1332. Move GroupNorm1 to common layers (used in poolformer + mobilevitv2). Keep ol custom ConvNeXt LayerNorm2d impl as LayerNormExp2d for reference.	2 years ago
nasnet.py	…
nest.py	…
nfnet.py	…
pit.py	…
pnasnet.py	…
poolformer.py	Add MobileVitV2 support. Fix #1332. Move GroupNorm1 to common layers (used in poolformer + mobilevitv2). Keep ol custom ConvNeXt LayerNorm2d impl as LayerNormExp2d for reference.	2 years ago
registry.py	…
regnet.py	…
res2net.py	…
resnest.py	…
resnet.py	Remove first_conv for resnetaa50 def	2 years ago
resnetv2.py	…
rexnet.py	…
selecsls.py	…
senet.py	…
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	…
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	…
twins.py	…
vgg.py	…
visformer.py	…
vision_transformer.py	Unbreak gamma remap impacting beit checkpoint load, version bump to 0.6.4	2 years ago
vision_transformer_hybrid.py	…
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	…