Models / meta / ConvNeXt-Base (384px, ImageNet-22k pretrained, fine-tuned on ImageNet-1k)

ConvNeXt-Base (384px, ImageNet-22k pretrained, fine-tuned on ImageNet-1k)

metavision

A modernized ConvNet base model pretrained on ImageNet-22k and fine-tuned on ImageNet-1k at 384x384 resolution.

imagevision

Specs

Context & limits

—

context window

—

max output

Lifecycle

Dates

released2022-01-01

Resources