pytorch-image-models

# PyTorch Image Models
- [What's New](#whats-new)
- [Introduction](#introduction)
- [Models](#models)
- [Features](#features)
- [Results](#results)
- [Getting Started (Documentation)](#getting-started-documentation)
- [Train, Validation, Inference Scripts](#train-validation-inference-scripts)
- [Awesome PyTorch Resources](#awesome-pytorch-resources)
- [Licenses](#licenses)
- [Citing](#citing)

## What's New

## November 3, 2026

* `reset_classifier()` and checkpoint reconstruction: fixes across ViT, EVA, BEiT, NaFlexViT, RepViT and iFormer
  preserve normalization placement and distillation settings when exporting / reloading models after changing the
  classifier or pooling. Also fix unpooled PiT export and EfficientFormerV2 with distillation disabled.
* NaFlex: fix ViT / EVA norm placement during conversion, support SwiGLU alignment for DINOv3 / Lingbot checkpoints,
  and preserve grayscale / non-RGB input channels in data loaders.
* Fix layer-wise LR decay grouping for RepViT, HGNet, MViTv2 and pre-norm ViTs, and InceptionNeXt feature sizes with
  `output_stride=8/16`.
* Release 1.0.31.

## October 24, 2026

* `forward_intermediates()` and `prune_intermediate_layers()` are now supported by every model. Newly added for CSPNet, NFNet, DLA, DenseNet (#2870, thanks [ghaith-mq](https://github.com/ghaith-mq)), CoaT, ConViT, ConvMixer, CrossViT, HRNet, Inception-v3, Inception-ResNet-v2, NASNet, PNASNet, SelecSLS, SENet, Sequencer2d, VGG, Visformer, Xception and Aligned Xception, with `prune_intermediate_layers()` for NaFlexViT and MobileNetV5 encoders. CoaT, ConViT, ConvMixer, CrossViT and Visformer gain `features_only` support.
* `prune_intermediate_layers()` fixes
  * `prune_head=True` removes the whole head (head norm, pre-logits layers, attention pooling) so the pruned model leaves no unused params (DDP w/o `find_unused_parameters`), except CoaT, CrossViT and HRNet when only some of their parallel scales / branches are taken. Pass `prune_head=False` to keep it.
  * Pruning a hierarchical model to an earlier stage removes the final norm and head sized for the last stage, `forward_features()` ends at the last kept feature and `num_features` / `head_hidden_size` match it. Pruning to the stem feature removes the stem pooling after it.
  * Fixes for grad checkpointing, `stop_early`, class token / post network removal, and TorchScript of pruned / `feature_cls='getter'` models across many families.
* `head_hidden_size` is the actual pre-logits (pooled) width in all models, including concat pooling (`catavgmax`) and after `reset_classifier()`. Pool types a model can't apply now raise at creation / reset instead of being silently ignored or failing in forward.
* Other fixes: VOLO `num_classes=0` output is the class token embedding (matching `forward_head(pre_logits=True)`), `vit_pe_core` `reset_classifier()` w/ a non `map` pool removes the attention pool, pool type export via `save_for_hf` reads the head's current pooling, and headless (`num_classes=0`) S