ConvNext

ConvNext model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224. It was introduced in the paper A ConvNet for the 2020s. The weights were converted from the convnext_small_22k_224.pth file presented in the official repository.

Downloads last month: 3

Safetensors

Model size

66.3M params

Tensor type

F32

Inference Examples

Image Classification

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Collection including cs-giung/convnext-v1-small-imagenet21k

ConvNeXt (ImageNet-21k)

Collection

5 items • Updated Jul 7