Skip to content

Convnext large

The classification variant of the ConvNeXt Large architecture.

Architecture Variable Value
Key in architecture_dict "2D.ConvNeXtLarge"
Input_shape (384x384)
Standardization None

Recommended alternative Input_shape is 224x224 pixels.

Warning

ConvNeXt models expect their inputs to be float or uint8 tensors of pixels with values in the [0-255] range. Standardization is applied inside the architecture.

Reference - Implementation

https://www.tensorflow.org/api_docs/python/tf/keras/applications/convnext

Reference - Publication

Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie. 10 Jan 2022. A ConvNet for the 2020s.
https://arxiv.org/abs/2201.03545