Convnext base

The classification variant of the ConvNeXt Base architecture.

Architecture Variable	Value
Key in architecture_dict	"3D.ConvNeXtBase"
Input_shape	(64, 64, 64)
Standardization	None

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

Solovyev, Roman & Kalinin, Alexandr & Gabruseva, Tatiana. (2021).
3D Convolutional Neural Networks for Stalled Brain Capillary Detection.
https://github.com/ZFTurbo/classification_models_3D

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