DeiT

Category: ViT · Code: timm/models/deit.py · Architectures: 16 · Pretrained weights: 24 (24 with ImageNet-1k results)

Data-efficient Image Transformers (DeiT) are Vision Transformers trained on ImageNet-1k only, optionally with a distillation token that learns from a CNN teacher. DeiT III models are trained with an improved recipe.

Papers

• Training data-efficient image transformers & distillation through attention
• DeiT III: Revenge of the ViT

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('deit_small_distilled_patch16_224.fb_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 (VisionTransformer with deit_tiny_patch16_224 at 224, VisionTransformerDistilled with deit_tiny_distilled_patch16_224 at 224), 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.