340 Commits (43225d110c6b6afaddac487019951c448ad31add)

 

All Branches   

Search

Author	SHA1	Message	Date
Ross Wightman	43225d110c	Unify drop connect vs drop path under 'drop path' name, switch all EfficientNet/MobilenetV3 refs to 'drop_path'. Update factory to handle new drop args.	4 years ago
Ross Wightman	f1d5f8a6c4	Update comments for Selective Kernel and DropBlock/Path impl, add skresnet34 weights	4 years ago
Ross Wightman	569419b38d	Tweak some comments, add SKNet models with weights to sotabench, remove an unused branch	4 years ago
Ross Wightman	91e2b33d72	Update results with latest NoisyStudent models and SelectiveKernel models	4 years ago
Ross Wightman	53c47479c4	Batch validation batch size adjustment, tweak L2 crop pct	4 years ago
Ross Wightman	08553e16b3	Merge branch 'master' into attention	4 years ago
Ross Wightman	fa38f24967	Update SK network configs, add weights for skresnet8 and skresnext50	4 years ago
Ross Wightman	f098fda2ca	Add map_location='cpu' to ModelEma resume, should improve #72	4 years ago
Ross Wightman	b9496995d8	Add L2-475 PyTorch preprocessing result, update sotabench for new weights	4 years ago
Ross Wightman	ba15ca47e8	Add ported EfficientNet-L2, B0-B7 NoisyStudent weights from TF TPU	4 years ago
Ross Wightman	5e6dbbaf30	Add CBAM for experimentation	4 years ago
Ross Wightman	d725991870	Remove debug print from ECA module	4 years ago
Ross Wightman	2a7d256fd5	Re-enable mem-efficient/jit activations after torchscript tests	4 years ago
Ross Wightman	f902bcd54c	Layer refactoring continues, ResNet downsample rewrite for proper dilation in 3x3 and avg_pool cases ... * select_conv2d -> create_conv2d * added create_attn to create attention module from string/bool/module * factor padding helpers into own file, use in both conv2d_same and avg_pool2d_same * add some more test eca resnet variants * minor tweaks, naming, comments, consistency	4 years ago
Ross Wightman	a99ec4e7d1	A bunch more layer reorg, splitting many layers into own files. Improve torchscript compatibility.	4 years ago
Ross Wightman	13746a33fc	Big move, layer modules and fn to timm/models/layers	4 years ago
Ross Wightman	f54612f648	Merge branch 'select_kernel' into attention	4 years ago
Ross Wightman	4defbbbaa8	Fix module name mistake, start layers sub-package	4 years ago
Ross Wightman	7011cd0902	A little bit of ECA cleanup	4 years ago
Ross Wightman	46471df7b2	Merge pull request #82 from VRandme/eca ... ECA-Net Efficient Channel Attention	4 years ago
Ross Wightman	d0eb59ef46	Remove unused default_init for EfficientNets, experimenting with fanout calc for #84	4 years ago
Ross Wightman	cade829105	Add EfficientNet-ES to sotabench	4 years ago
Chris Ha	e6a762346a	Implement Adaptive Kernel selection ... When channel size is given, calculate adaptive kernel size according to original paper. Otherwise use the given kernel size(k_size), which defaults to 3	4 years ago
Ross Wightman	13e8da2b46	SelectKernel split_input works best when input channels split like grouped conv, but output is full width. Disable zero_init for SK nets, seems a bad combo.	4 years ago
Chris Ha	6db087a1ff	Merge remote-tracking branch 'upstream/master' into eca	4 years ago
Chris Ha	904c618040	Update EcaModule.py ... Make pylint happy (commas, unused imports, missed imports)	4 years ago
Chris Ha	db91ba053b	EcaModule(CamelCase) ... CamelCased EcaModule. Renamed all instances of ecalayer to EcaModule. eca_module.py->EcaModule.py	4 years ago
Ross Wightman	5eb0e363a6	Update README.md	4 years ago
Ross Wightman	5c4991a088	Add PyTorch trained EfficientNet-ES weights from Andrew Lavin	4 years ago
Chris Ha	d04ff95eda	Merge branch 'master' into eca	4 years ago
Chris Ha	d63ae121d5	Clean up eca_module code ... functionally similar adjusted rwightman's version of reshaping and viewing. Use F.pad for circular eca version for cleaner code	4 years ago
Chris Ha	b0d45fd09c	Merge remote-tracking branch 'upstream/master'	4 years ago
Ross Wightman	d66819d1f3	Indentation mistake. Fixes #81	4 years ago
Ross Wightman	65cda1c63f	Merge pull request #83 from andravin/validation-batch-size-multiplier ... Added commandline argument validation-batch-size-multiplier.	4 years ago
Chris Ha	f87fcd7e88	Implement Eca modules ... implement ECA module by 1. adopting original eca_module.py into models folder 2. adding use_eca layer besides every instance of SE layer	4 years ago
Chris Ha	697e05cb3e	Merge remote-tracking branch 'upstream/master'	4 years ago
Andrew Lavin	b72013def8	Added commandline argument validation-batch-size-multiplier with default set to 1.	4 years ago
Ross Wightman	4808b3c32f	Bump version for PyPi update, fix few out of date README items/mistakes, add README updates for TF EfficientNet-B8 (RandAugment)	4 years ago
Ross Wightman	5c85389e26	Update README.md	4 years ago
Ross Wightman	820b73d280	Update README.md	4 years ago
Ross Wightman	82c0a2ff12	Update README.md ... Fix relative paths (I think)	4 years ago
Ross Wightman	1ffd2d0694	Add results/README.md	4 years ago
Chris Ha	89a32454e1	Merge remote-tracking branch 'upstream/master'	4 years ago
Ross Wightman	7d07ebb660	Adding some configs to sknet, incl ResNet50 variants from 'Compounding ... Assembled Techniques' paper and original SKNet50	4 years ago
Ross Wightman	a9d2424fd1	Add separate zero_init_last_bn function to support more block variety without a mess	4 years ago
Ross Wightman	355aa152d5	Just leave it float for now, will look at fp16 later. Remove unused reference code.	4 years ago
Ross Wightman	ef457555d3	BlockDrop working on GPU	4 years ago
Ross Wightman	3ff19079f9	Missed nn_ops.py from last commit	4 years ago
Ross Wightman	9f11b4e8a2	Add ConvBnAct layer to parallel integrated SelectKernelConv, add support for DropPath and DropBlock to ResNet base and SK blocks	4 years ago
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	4 years ago