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 f3134973b5
Add the MnasNet-B1 variant weights, add A1/B1 model names as in the stand-alone repo, remove a bit of unused code
5 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 Cleanup model_factory imports, consistent __all__ for models, fixed inception_v4 weight url 6 years ago
dpn.py Cleanup model_factory imports, consistent __all__ for models, fixed inception_v4 weight url 6 years ago
gen_efficientnet.py Add the MnasNet-B1 variant weights, add A1/B1 model names as in the stand-alone repo, remove a bit of unused code 5 years ago
gluon_resnet.py Cleanup model_factory imports, consistent __all__ for models, fixed inception_v4 weight url 6 years ago
helpers.py Add per model crop pct, interpolation defaults, tie it all together 6 years ago
inception_resnet_v2.py Cleanup model_factory imports, consistent __all__ for models, fixed inception_v4 weight url 6 years ago
inception_v3.py Cleanup model_factory imports, consistent __all__ for models, fixed inception_v4 weight url 6 years ago
inception_v4.py Cleanup model_factory imports, consistent __all__ for models, fixed inception_v4 weight url 6 years ago
median_pool.py Initial commit, puting some ol pieces together 6 years ago
model_factory.py Ported Tensorflow pretrained EfficientNet weights and some model cleanup 6 years ago
pnasnet.py Cleanup model_factory imports, consistent __all__ for models, fixed inception_v4 weight url 6 years ago
resnet.py Replace ResNet-34 default weights with a great result from my experiments. 6 years ago
senet.py Missed a few models in the model/_all_ list for senet 6 years ago
test_time_pool.py Add native PyTorch weights for EfficientNet-B0 w/ top-1 > 76.9 6 years ago
xception.py Cleanup model_factory imports, consistent __all__ for models, fixed inception_v4 weight url 6 years ago