ConvNeXt — Torchvision 0.16 documentation (original) (raw)
The ConvNeXt model is based on the A ConvNet for the 2020s paper.
Model builders¶
The following model builders can be used to instantiate a ConvNeXt model, with or without pre-trained weights. All the model builders internally rely on thetorchvision.models.convnext.ConvNeXt base class. Please refer to the source code for more details about this class.
| convnext_tiny(*[, weights, progress]) | ConvNeXt Tiny model architecture from the A ConvNet for the 2020s paper. |
|---|---|
| convnext_small(*[, weights, progress]) | ConvNeXt Small model architecture from the A ConvNet for the 2020s paper. |
| convnext_base(*[, weights, progress]) | ConvNeXt Base model architecture from the A ConvNet for the 2020s paper. |
| convnext_large(*[, weights, progress]) | ConvNeXt Large model architecture from the A ConvNet for the 2020s paper. |