NaFlex ViT

Category: ViT · Code: timm/models/naflexvit.py · Architectures: 8 · Pretrained weights: 5 (3 with ImageNet-1k results)

A Vision Transformer with the patch embedding and position encoding in one module, supporting pre-patchified inputs with variable aspect ratio and resolution (NaFlex), FlexiViT variable patch size and NaViT factorized position embeddings.

Papers

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• FlexiViT: One Model for All Patch Sizes
• Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
• SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Usage

See the Quickstart for loading pretrained weights, image preprocessing and fine-tuning, and Feature Extraction for using the models as backbones.

>>> import timm
>>> model = timm.create_model('naflexvit_base_patch16_parfac_gap.e300_s576_in1k', pretrained=True)
>>> data_config = timm.data.resolve_model_data_config(model)

Model API support

✓ supported, ✓ (square) works for square sizes only, ✗ not supported, – not needed (the model already accepts any input size). Checked by running each feature on a randomly initialized model (NaFlexVit with naflexvit_base_patch16_parfac_gap at 384), other architectures of the same class are expected to behave the same. See the Model API page for details.

Architectures

GMACs and parameter counts are for the default input size and classifier of each architecture, from the benchmark results.

Pretrained weights

Top-1 is ImageNet-1k validation accuracy from results-imagenet.csv at the listed eval size, - if the weight has no ImageNet-1k result (e.g. pretraining or image-text weights). Classes is the size of the pretrained classifier, none for weights without one.