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.
pytorch-image-models/timm/models
Ross Wightman 90a01f47d1
hrnet features_only pretrained weight loading issue. Fix #232.
4 years ago
..
layers AdaptiveAvgPool2d -> mean((2,3)) for all SE/attn layers to avoid NaN with AMP + channels_last layout. See https://github.com/pytorch/pytorch/issues/43992 4 years ago
pruned
__init__.py
cspnet.py Add CSPResNet50 weights, 79.6 top-1 at 256x256 4 years ago
densenet.py
dla.py
dpn.py
efficientnet.py Add new EfficientNet-B3 and RegNetY-3.2GF weights, both just over 82 top-1 4 years ago
efficientnet_blocks.py AdaptiveAvgPool2d -> mean((2,3)) for all SE/attn layers to avoid NaN with AMP + channels_last layout. See https://github.com/pytorch/pytorch/issues/43992 4 years ago
efficientnet_builder.py
factory.py
features.py
gluon_resnet.py fix test_model_default_cfgs 4 years ago
gluon_xception.py
helpers.py Fix a few more issues related to #216 w/ TResNet (space2depth) and FP16 weights in wide resnets. Also don't completely dump pretrained weights in in_chans != 1 or 3 cases. 4 years ago
hrnet.py hrnet features_only pretrained weight loading issue. Fix #232. 4 years ago
inception_resnet_v2.py
inception_v3.py fix test_model_default_cfgs 4 years ago
inception_v4.py
mobilenetv3.py Fix MobileNetV3 crash with global_pool='', output consistent with other models but not equivalent due to efficient head. 4 years ago
nasnet.py
pnasnet.py
registry.py
regnet.py Add new EfficientNet-B3 and RegNetY-3.2GF weights, both just over 82 top-1 4 years ago
res2net.py
resnest.py fix test_model_default_cfgs 4 years ago
resnet.py fix test_model_default_cfgs 4 years ago
rexnet.py AdaptiveAvgPool2d -> mean((2,3)) for all SE/attn layers to avoid NaN with AMP + channels_last layout. See https://github.com/pytorch/pytorch/issues/43992 4 years ago
selecsls.py fix test_model_default_cfgs 4 years ago
senet.py AdaptiveAvgPool2d -> mean((2,3)) for all SE/attn layers to avoid NaN with AMP + channels_last layout. See https://github.com/pytorch/pytorch/issues/43992 4 years ago
sknet.py fix test_model_default_cfgs 4 years ago
tresnet.py AdaptiveAvgPool2d -> mean((2,3)) for all SE/attn layers to avoid NaN with AMP + channels_last layout. See https://github.com/pytorch/pytorch/issues/43992 4 years ago
vovnet.py
xception.py
xception_aligned.py fix test_model_default_cfgs 4 years ago