* Add some newly trained MobileNet-V2 models trained with latest h-params, rand augment. They compare quite favourably to EfficientNet-Lite
* 3.5M param MobileNet-V2 100 @ 73%
* 4.5M param MobileNet-V2 110d @ 75%
* 6.1M param MobileNet-V2 140 @ 76.5%
* 5.8M param MobileNet-V2 120d @ 77.3%
### March 18, 2020
* Add EfficientNet-Lite models w/ weights ported from [Tensorflow TPU](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite)
* Add RandAugment trained ResNeXt-50 32x4d weights with 79.8 top-1. Trained by [Andrew Lavin](https://github.com/andravin) (see Training section for hparams)
### Feb 29, 2020
* New MobileNet-V3 Large weights trained from stratch with this code to 75.77% top-1
* IMPORTANT CHANGE - default weight init changed for all MobilenetV3 / EfficientNet / related models
* 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.
### Aug 12, 2020
* New/updated weights from training experiments
* EfficientNet-B3 - 82.1 top-1 (vs 81.6 for official with AA and 81.9 for AdvProp)
@ -54,14 +89,3 @@ Bunch of changes:
* 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
### April 5, 2020
* Add some newly trained MobileNet-V2 models trained with latest h-params, rand augment. They compare quite favourably to EfficientNet-Lite
* 3.5M param MobileNet-V2 100 @ 73%
* 4.5M param MobileNet-V2 110d @ 75%
* 6.1M param MobileNet-V2 140 @ 76.5%
* 5.8M param MobileNet-V2 120d @ 77.3%
### March 18, 2020
* Add EfficientNet-Lite models w/ weights ported from [Tensorflow TPU](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite)
* Add RandAugment trained ResNeXt-50 32x4d weights with 79.8 top-1. Trained by [Andrew Lavin](https://github.com/andravin) (see Training section for hparams)
Little to no care has been taken to be Python 2.x friendly and will not support it. If you run into any challenges running on Windows, or other OS, I'm definitely open to looking into those issues so long as it's in a reproducible (read Conda) environment.
PyTorch versions 1.4, 1.5.x, and 1.6 have been tested with this code.
PyTorch versions 1.4, 1.5.x, 1.6, and 1.7 have been tested with this code.
I've tried to keep the dependencies minimal, the setup is as per the PyTorch default install instructions for Conda:
CSV files containing an ImageNet-1K validation and OOD test set validation results for all included models with pretrained weights and default configurations is located [here](https://github.com/rwightman/pytorch-image-models/tree/master/results).
CSV files containing an ImageNet-1K validation and out-of-distribution (OOD) test set validation results for all included models with pretrained weights and default configurations is located [here](https://github.com/rwightman/pytorch-image-models/tree/master/results).
## Self-trained Weights
I've leveraged the training scripts in this repository to train a few of the models with to good levels of performance.
For the models below, the model code and weight porting from Tensorflow or MXNet Gluon to Pytorch was done by myself. There are weights/models ported by others included in this repository, they are not listed below.
Models with `*tfp` next to them were scored with `--tf-preprocessing` flag.
The `tf_efficientnet`, `tf_mixnet` models require an equivalent for 'SAME' padding as their arch results in asymmetric padding. I've added this in the model creation wrapper, but it does come with a performance penalty.
For weights ported from other deep learning frameworks (Tensorflow, MXNet GluonCV) or copied from other PyTorch sources, please see the full results tables for ImageNet and various OOD test sets at in the [results tables](https://github.com/rwightman/pytorch-image-models/tree/master/results).
Ross Wightman
4 years ago