ResNet
Building and adapting convolutional networks with residual blocks that learn corrections to an identity mapping, including the effect of skip connections on training deeper image models.
Also searchable as: ResNets
Prerequisites
Residual blocks extend convolutional network design.
Recommended reference
Reviewed sources
Primary and first-party material reviewed for this editorial summary. These citations are separate from the AI consensus score above.
- He et al.: Deep Residual Learning for Image Recognition
Residual block design and the optimization of deep image networks.
- Torchvision: ResNet
Official model-family documentation covering ResNet builders, pretrained weights and the stride-placement difference in the Torchvision bottleneck implementation.
- Keras: ResNet models
Official ResNet and ResNetV2 APIs explaining model variants, input preprocessing and options for transfer learning and feature extraction.
Notes from AI deep research
Related skills
- → is subcategory of: Convolutional Neural Networks