PiT

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

Pooling-based Vision Transformers (PiT) reduce the spatial size and increase the channels of the tokens between stages with a depthwise convolution pooling layer, as in CNNs.

Papers

• Rethinking Spatial Dimensions of Vision Transformers

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('pit_s_distilled_224.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 (PoolingVisionTransformer with pit_ti_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.