huggingface/pytorch-image-models v0.9.16 on GitHub

Next-ViT models added. Adapted from https://github.com/bytedance/Next-ViT
HGNet and PP-HGNetV2 models added. Adapted from https://github.com/PaddlePaddle/PaddleClas by SeeFun
Removed setup.py, moved to pyproject.toml based build supported by PDM
Add updated model EMA impl using _for_each for less overhead
Support device args in train script for non GPU devices
Other misc fixes and small additions
Min supported Python version increased to 3.8
Release 0.9.16

Datasets & transform refactoring

HuggingFace streaming (iterable) dataset support (--dataset hfids:org/dataset)
Webdataset wrapper tweaks for improved split info fetching, can auto fetch splits from supported HF hub webdataset
Tested HF datasets and webdataset wrapper streaming from HF hub with recent timm ImageNet uploads to https://huggingface.co/timm
Make input & target column/field keys consistent across datasets and pass via args
Full monochrome support when using e:g: --input-size 1 224 224 or --in-chans 1, sets PIL image conversion appropriately in dataset
Improved several alternate crop & resize transforms (ResizeKeepRatio, RandomCropOrPad, etc) for use in PixParse document AI project
Add SimCLR style color jitter prob along with grayscale and gaussian blur options to augmentations and args
Allow train without validation set (--val-split '') in train script
Add --bce-sum (sum over class dim) and --bce-pos-weight (positive weighting) args for training as they're common BCE loss tweaks I was often hard coding

huggingface/pytorch-image-models v0.9.16 Release v0.9.16 on GitHub