A base ConvNeXtV2 model pre-trained on ImageNet-22K at 384x384 resolution. It combines modern convolutional design with transformer-like properties and is distributed on Hugging Face for use with the Transformers library.
Convnextv2 Base 22k 384 sits in PulseGate's Other AI category. It focuses on classifying images with high accuracy using an improved convolutional architecture pre-trained on large datasets. It is built as an open-source project for developers. The project is open source (Open Source). It runs on the web and API.
It is developed by Meta AI, and it first shipped in 2023. The GitHub repository has been archived. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do