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 2568ffc5ef Merge branch 'master' into attn_update		3 years ago
..
layers	Improve performance of HaloAttn, change default dim calc. Some cleanup / fixes for byoanet. Rename resnet26ts to tfs to distinguish (extra fc).	3 years ago
pruned	…
__init__.py	wip xcit	4 years ago
byoanet.py	Improve performance of HaloAttn, change default dim calc. Some cleanup / fixes for byoanet. Rename resnet26ts to tfs to distinguish (extra fc).	3 years ago
byobnet.py	Improve performance of HaloAttn, change default dim calc. Some cleanup / fixes for byoanet. Rename resnet26ts to tfs to distinguish (extra fc).	3 years ago
cait.py	…
coat.py	…
convit.py	…
cspnet.py	…
densenet.py	…
dla.py	…
dpn.py	…
efficientnet.py	Add gc_efficientnetv2_rw_t weights (global context instead of SE attn). Add TF XL weights even though the fine-tuned ones don't validate that well. Change default arg for GlobalContext to use scal (mul) mode.	4 years ago
efficientnet_blocks.py	…
efficientnet_builder.py	…
factory.py	…
features.py	…
ghostnet.py	Fix a few issues loading pretrained vit/bit npz weights w/ num_classes=0 __init__ arg. Missed a few other small classifier handling detail on Mlp, GhostNet, Levit. Should fix #713	4 years ago
gluon_resnet.py	…
gluon_xception.py	…
hardcorenas.py	…
helpers.py	…
hrnet.py	…
hub.py	…
inception_resnet_v2.py	…
inception_v3.py	…
inception_v4.py	…
levit.py	Fix a few issues loading pretrained vit/bit npz weights w/ num_classes=0 __init__ arg. Missed a few other small classifier handling detail on Mlp, GhostNet, Levit. Should fix #713	4 years ago
mlp_mixer.py	Add gMLP-S weights, 79.6 top-1	4 years ago
mobilenetv3.py	…
nasnet.py	…
nest.py	Use bicubic interpolation in resize_pos_embed()	4 years ago
nfnet.py	…
pit.py	…
pnasnet.py	…
registry.py	…
regnet.py	…
res2net.py	…
resnest.py	…
resnet.py	…
resnetv2.py	Fix features for resnetv2_50t	4 years ago
rexnet.py	…
selecsls.py	…
senet.py	…
sknet.py	…
swin_transformer.py	…
tnt.py	…
tresnet.py	…
twins.py	…
vgg.py	…
visformer.py	Fix a few issues loading pretrained vit/bit npz weights w/ num_classes=0 __init__ arg. Missed a few other small classifier handling detail on Mlp, GhostNet, Levit. Should fix #713	4 years ago
vision_transformer.py	Fix ViT SAM weight compat as weights at URL changed to not use repr layer. Fix #825. Tweak optim test.	3 years ago
vision_transformer_hybrid.py	AugReg release	4 years ago
vovnet.py	…
xception.py	…
xception_aligned.py	…
xcit.py	Allow act_layer switch for xcit, fix in_chans for some variants	4 years ago