Commit Graph

26 Commits (355aa152d5c89f210ae0771f800598409807dacf)

Author SHA1 Message Date
Ross Wightman 9f11b4e8a2 Add ConvBnAct layer to parallel integrated SelectKernelConv, add support for DropPath and DropBlock to ResNet base and SK blocks 2020-02-01 22:11:00 -08:00
Ross Wightman cefc9b7761 Move SelectKernelConv to conv2d_layers and more
* always apply attention in SelectKernelConv, leave MixedConv for no attention alternative
* make MixedConv torchscript compatible
* refactor first/previous dilation name to make more sense in ResNet* networks
2020-02-01 22:11:00 -08:00
Ross Wightman 58e28dc7e7 Move Selective Kernel blocks/convs to their own sknet.py file 2020-02-01 22:11:00 -08:00
Ross Wightman a93bae6dc5 A SelectiveKernelBasicBlock for more experiments 2020-02-01 22:11:00 -08:00
Ross Wightman ad087b4b17 Missed bias=False in selection conv 2020-02-01 22:11:00 -08:00
Ross Wightman c8b3d6b81a Initial impl of Selective Kernel Networks. Very much a WIP. 2020-02-01 22:11:00 -08:00
Ross Wightman 12dbc74742 New ResNet50 JSD + RandAugment weights 2020-01-31 10:55:54 -08:00
Ross Wightman 2f41905ba5 Update ResNet50 weights to AuxMix trained 78.994 top-1. A few commentes re 'tiered_narrow' tn variant. 2020-01-12 17:55:58 -08:00
Ross Wightman a28117ea46 Add tiered narrow ResNet (tn) and weights for seresnext26tn_32x4d 2020-01-11 11:29:01 -08:00
Ross Wightman 53001dd292 ResNet / Res2Net additions:
* ResNet torchscript compat
* output_stride arg supported to limit network stride via dilations (support for dilation added to Res2Net)
* allow activation layer to be changed via act_layer arg
2020-01-01 17:15:56 -08:00
Ross Wightman 19fc205a4d Update comments on the new SE-ResNeXt26 models 2019-12-28 17:33:10 -08:00
rwightman 1f4498f217 Add ResNet deep tiered stem and model weights for seresnext26t_32x4d and seresnext26d_32x4d 2019-12-28 11:43:50 -08:00
Ross Wightman 3bef524f9c Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment. 2019-11-29 17:56:36 -08:00
Ross Wightman 5a0a8de7e3 ResNet updates:
* remove redundant GluonResNet model/blocks and use the code in ResNet for Gluon weights
* change SEModules back to using AdaptiveAvgPool instead of mean, PyTorch issue long fixed
2019-11-28 17:04:35 -08:00
Ross Wightman b93fcf0708 Add Facebook Research Semi-Supervised and Semi-Weakly Supervised ResNet model weights. 2019-10-19 17:05:37 -07:00
rwightman adbf770f16 Add Res2Net and DLA models w/ pretrained weights. Update sotabench. 2019-09-04 17:06:42 -07:00
Ross Wightman fac58f609a Add RAdam, NovoGrad, Lookahead, and AdamW optimizers, a few ResNet tweaks and scheduler factory tweak.
* Add some of the trendy new optimizers. Decent results but not clearly better than the standards.
* Can create a None scheduler for constant LR
* ResNet defaults to zero_init of last BN in residual
* add resnet50d config
2019-08-28 00:14:10 -07:00
Ross Wightman 3d9be78fc6 A bit more ResNet cleanup.
* add inplace=True back
* minor comment improvements
* few clarity changes
2019-07-19 16:44:35 -07:00
Ross Wightman 33436fafad Add weights for ResNeXt50d model 2019-07-19 14:09:10 -07:00
Ross Wightman e78cd79073 Move ResNet additions for Gluon into main ResNet impl. Add ResNet-26 and ResNet-26d models with weights. 2019-07-14 18:17:35 -07:00
Ross Wightman 9b0070edc9 Add two comments back, fix typo 2019-06-29 16:44:25 -07:00
Ross Wightman b8762cc67d Model updates. Add my best ResNet50 weights top-1=78.47. Add some other torchvision weights.
* Remove some models that don't exist as pretrained an likely never will (se)resnext152
* Add some torchvision weights as tv_ for models that I have added better weights for
* Add wide resnet recently added to torchvision along with resnext101-32x8d
* Add functionality to model registry to allow filtering on pretrained weight presence
2019-06-29 15:50:33 -07:00
Ross Wightman 171c0b88b6 Add model registry and model listing fns, refactor model_factory/create_model fn 2019-06-23 18:22:16 -07:00
Ross Wightman 8512436436 Add instagram pretrained ResNeXt models from https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/, update README 2019-06-23 12:29:02 -07:00
Ross Wightman 6cc214bd7a Consistency in model entrypoints
* move pretrained entrypoint arg to first pos to be closer to torchvision/hub
* change DPN weight URLS to my github location
2019-06-20 23:29:44 -07:00
Ross Wightman aa4354f466 Big re-org, working towards making pip/module as 'timm' 2019-06-19 17:20:51 -07:00