* Add LeViT, Visformer, Convit (PR by Aman Arora), Twins (PR by paper authors) transformer models
* Cleanup input_size/img_size override handling and testing for all vision transformer models
* Add `efficientnetv2_rw_m` model and weights (started training before official code). 84.8 top-1, 53M params.
### May 14, 2021
* Add EfficientNet-V2 official model defs w/ ported weights from official [Tensorflow/Keras](https://github.com/google/automl/tree/master/efficientnetv2) impl.
* Add Swin Transformer models and weights from https://github.com/microsoft/Swin-Transformer
### April 12, 2021
* Add ECA-NFNet-L1 (slimmed down F1 w/ SiLU, 41M params) trained with this code. 84% top-1 @ 320x320. Trained at 256x256.
* Add EfficientNet-V2S model (unverified model definition) weights. 83.3 top-1 @ 288x288. Only trained single res 224. Working on progressive training.
* Add ByoaNet model definition (Bring-your-own-attention) w/ SelfAttention block and corresponding SA/SA-like modules and model defs
* Change feature extraction for pre-activation nets (NFNets, ResNetV2) to return features before activation.
### Feb 18, 2021
* Add pretrained weights and model variants for NFNet-F* models from [DeepMind Haiku impl](https://github.com/deepmind/deepmind-research/tree/master/nfnets).
* Models are prefixed with `dm_`. They require SAME padding conv, skipinit enabled, and activation gains applied in act fn.
* These models are big, expect to run out of GPU memory. With the GELU activiation + other options, they are roughly 1/2 the inference speed of my SiLU PyTorch optimized `s` variants.
* Original model results are based on pre-processing that is not the same as all other models so you'll see different results in the results csv (once updated).
* Matching the original pre-processing as closely as possible I get these results:
*`dm_nfnet_f6` - 86.352
*`dm_nfnet_f5` - 86.100
*`dm_nfnet_f4` - 85.834
*`dm_nfnet_f3` - 85.676
*`dm_nfnet_f2` - 85.178
*`dm_nfnet_f1` - 84.696
*`dm_nfnet_f0` - 83.464
### Feb 16, 2021
* Add Adaptive Gradient Clipping (AGC) as per https://arxiv.org/abs/2102.06171. Integrated w/ PyTorch gradient clipping via mode arg that defaults to prev 'norm' mode. For backward arg compat, clip-grad arg must be specified to enable when using train.py.
* PyTorch global norm of 1.0 (old behaviour, always norm), `--clip-grad 1.0`
* PyTorch value clipping of 10, `--clip-grad 10. --clip-mode value`
* AGC performance is definitely sensitive to the clipping factor. More experimentation needed to determine good values for smaller batch sizes and optimizers besides those in paper. So far I've found .001-.005 is necessary for stable RMSProp training w/ NFNet/NF-ResNet.
### Feb 12, 2021
* Update Normalization-Free nets to include new NFNet-F (https://arxiv.org/abs/2102.06171) model defs
* More model archs, incl a flexible ByobNet backbone ('Bring-your-own-blocks')
* GPU-Efficient-Networks (https://github.com/idstcv/GPU-Efficient-Networks), impl in `byobnet.py`
* RepVGG (https://github.com/DingXiaoH/RepVGG), impl in `byobnet.py`
* classic VGG (from torchvision, impl in `vgg`)
* Refinements to normalizer layer arg handling and normalizer+act layer handling in some models
* Default AMP mode changed to native PyTorch AMP instead of APEX. Issues not being fixed with APEX. Native works with `--channels-last` and `--torchscript` model training, APEX does not.
* Fix a few bugs introduced since last pypi release
### Feb 8, 2021
* Add several ResNet weights with ECA attention. 26t & 50t trained @ 256, test @ 320. 269d train @ 256, fine-tune @320, test @ 352.
* Remove separate tiered (`t`) vs tiered_narrow (`tn`) ResNet model defs, all `tn` changed to `t` and `t` models removed (`seresnext26t_32x4d` only model w/ weights that was removed).
* Support model default_cfgs with separate train vs test resolution `test_input_size` and remove extra `_320` suffix ResNet model defs that were just for test.
### Jan 30, 2021
* Add initial "Normalization Free" NF-RegNet-B* and NF-ResNet model definitions based on [paper](https://arxiv.org/abs/2101.08692)
### Jan 25, 2021
* Add ResNetV2 Big Transfer (BiT) models w/ ImageNet-1k and 21k weights from https://github.com/google-research/big_transfer
* Add official R50+ViT-B/16 hybrid models + weights from https://github.com/google-research/vision_transformer
* ImageNet-21k ViT weights are added w/ model defs and representation layer (pre logits) support
* NOTE: ImageNet-21k classifier heads were zero'd in original weights, they are only useful for transfer learning
* Add model defs and weights for DeiT Vision Transformer models from https://github.com/facebookresearch/deit
* Refactor dataset classes into ImageDataset/IterableImageDataset + dataset specific parser classes
* Add Tensorflow-Datasets (TFDS) wrapper to allow use of TFDS image classification sets with train script
* Test with PyTorch 1.7 and fix a small top-n metric view vs reshape issue.
* Convert newly added 224x224 Vision Transformer weights from official JAX repo. 81.8 top-1 for B/16, 83.1 L/16.
* Support PyTorch 1.7 optimized, native SiLU (aka Swish) activation. Add mapping to 'silu' name, custom swish will eventually be deprecated.
* Fix regression for loading pretrained classifier via direct model entrypoint functions. Didn't impact create_model() factory usage.
* PyPi release @ 0.3.0 version!
### Oct 26, 2020
* Update Vision Transformer models to be compatible with official code release at https://github.com/google-research/vision_transformer
* Add Vision Transformer weights (ImageNet-21k pretrain) for 384x384 base and large models converted from official jax impl
* ViT-B/16 - 84.2
* ViT-B/32 - 81.7
* ViT-L/16 - 85.2
* ViT-L/32 - 81.5
### Oct 21, 2020
* Weights added for Vision Transformer (ViT) models. 77.86 top-1 for 'small' and 79.35 for 'base'. Thanks to [Christof](https://www.kaggle.com/christofhenkel) for training the base model w/ lots of GPUs.
### Oct 13, 2020
* Initial impl of Vision Transformer models. Both patch and hybrid (CNN backbone) variants. Currently trying to train...
* Adafactor and AdaHessian (FP32 only, no AMP) optimizers
* EdgeTPU-M (`efficientnet_em`) model trained in PyTorch, 79.3 top-1
* Pip release, doc updates pending a few more changes...
* Support for native Torch AMP and channels_last memory format added to train/validate scripts (`--channels-last`, `--native-amp` vs `--apex-amp`)
* Models tested with channels_last on latest NGC 20.08 container. AdaptiveAvgPool in attn layers changed to mean((2,3)) to work around bug with NHWC kernel.
* All models support the `features_only=True` argument for `create_model` call to return a network that extracts features from the deepest layer at each stride.
* DenseNet models updated with memory efficient addition from torchvision (fixed a bug), blur pooling and deep stem additions
* VoVNet V1 and V2 models added, 39 V2 variant (ese_vovnet_39b) trained to 79.3 top-1
* Activation factory added along with new activations:
* select act at model creation time for more flexibility in using activations compatible with scripting or tracing (ONNX export)
* hard_mish (experimental) added with memory-efficient grad, along with ME hard_swish
* context mgr for setting exportable/scriptable/no_jit states
* Norm + Activation combo layers added with initial trial support in DenseNet and VoVNet along with impl of EvoNorm and InplaceAbn wrapper that fit the interface
* Torchscript works for all but two of the model types as long as using Pytorch 1.5+, tests added for this
* Some import cleanup and classifier reset changes, all models will have classifier reset to nn.Identity on reset_classifer(0) call
* Prep for 0.1.28 pip release
### May 12, 2020
* Add ResNeSt models (code adapted from https://github.com/zhanghang1989/ResNeSt, paper https://arxiv.org/abs/2004.08955))
### May 3, 2020
* Pruned EfficientNet B1, B2, and B3 (https://arxiv.org/abs/2002.08258) contributed by [Yonathan Aflalo](https://github.com/yoniaflalo)
### May 1, 2020
* Merged a number of execellent contributions in the ResNet model family over the past month
* BlurPool2D and resnetblur models initiated by [Chris Ha](https://github.com/VRandme), I trained resnetblur50 to 79.3.
* TResNet models and SpaceToDepth, AntiAliasDownsampleLayer layers by [mrT23](https://github.com/mrT23)
* ecaresnet (50d, 101d, light) models and two pruned variants using pruning as per (https://arxiv.org/abs/2002.08258) by [Yonathan Aflalo](https://github.com/yoniaflalo)
* 200 pretrained models in total now with updated results csv in results folder
