C-RADIOv4-SO400M

This model performs visual feature extraction. For instance, RADIO generates image embeddings that can be used by a downstream model to classify images. C-RADIOv4 models are available in multiple sizes: * Shape-Optimized (431M parameters). * Huge (653M parameters). The embeddings generated by this model are expected to be used by a downstream application. For example:

翻訳準備中のため原文を表示しています