ResNetV2 (BiT)

Category: CNN · Code: timm/models/resnetv2.py · Architectures: 20 · Pretrained weights: 24 (18 with ImageNet-1k results)

Pre-activation ResNet (v2) with Group Normalization and Weight Standardization as used by Big Transfer (BiT), with the original BiT weights. Also supports the non pre-activation variant used as the hybrid Vision Transformer backbone.

Papers

• Big Transfer (BiT): General Visual Representation Learning
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Knowledge distillation: A good teacher is patient and consistent
• Identity Mappings in Deep Residual Networks

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('resnetv2_50.a1h_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 (ResNetV2 with resnetv2_18 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.

Weights are grouped by source: the paper or origin given in the pretrained config, else a Hub organization other than timm, else the first part of the pretrained tag (architecture.tag). Sources with a single weight are listed under other.

goog tags

ra4 tags

a1h tags

ah tags