dudcjs2779
/

anime-style-tag-clip

Zero-Shot Image Classification

Model card Files Files and versions

anime-style-tag-clip

This model weight is based on eva02_base_patch16_clip.
The dataset size is small, which may result in slightly reduced generalization performance of the model.

Dataset

I trained this model with anime-style image-tag data.
Train: 29187
Valid: 3000

Validation results

R@1: 0.87733
R@5: 0.96767
R@10: 0.98233

Training & Inference code

https://github.com/dudcjs2779/tag-clip.git

Downloads last month: 17

Safetensors

Model size

0.1B params

Tensor type

F32

·

Model tree for dudcjs2779/anime-style-tag-clip

Base model

timm/eva02_base_patch16_clip_224.merged2b_s8b_b131k

Finetuned

(1)

this model

Space using dudcjs2779/anime-style-tag-clip 1