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/models
Ross Wightman db8ad25a23
MobileNetV3 appears correct based on paper update, cleaned up comments and compacted last block def
6 years ago
..
__init__.py Uniform pretrained model handling. 6 years ago
adaptive_avgmax_pool.py Fix pooling in mnasnet, more sensible default for AMP opt level 6 years ago
conv2d_same.py Add support for tflite mnasnet pretrained weights and included spnasnet pretrained weights of my own. 6 years ago
densenet.py Add per model crop pct, interpolation defaults, tie it all together 6 years ago
dpn.py Identity is not the same thing as equality in Python 6 years ago
genmobilenet.py MobileNetV3 appears correct based on paper update, cleaned up comments and compacted last block def 6 years ago
helpers.py Add per model crop pct, interpolation defaults, tie it all together 6 years ago
inception_resnet_v2.py Add per model crop pct, interpolation defaults, tie it all together 6 years ago
inception_v4.py Add per model crop pct, interpolation defaults, tie it all together 6 years ago
median_pool.py Initial commit, puting some ol pieces together 6 years ago
model_factory.py Add MobileNetV3 and associated changes hard-swish, hard-sigmoid, efficient head, etc 6 years ago
pnasnet.py Add per model crop pct, interpolation defaults, tie it all together 6 years ago
resnet.py Add checkpoint clean script, add link to pretrained resnext50 weights 6 years ago
senet.py Add seresnet26_32x4d cfg and weights + interpolation str->PIL enum fn 6 years ago
test_time_pool.py Add per model crop pct, interpolation defaults, tie it all together 6 years ago
xception.py Add per model crop pct, interpolation defaults, tie it all together 6 years ago