japanese clip vit b 16 EU AI Act Compliance Profile

rinna/japanese-clip-vit-b-16

This is a Japanese CLIP (Contrastive Language-Image Pre-Training) model trained by rinna Co., Ltd..

Please see japanese-clip for the other available models.

How to use the model

1. Install package

$ pip install git+https://github.com/rinnakk/japanese-clip.git

1. Run

import io
import requests
from PIL import Image
import torch
import japanese_clip as ja_clip

device = "cuda" if torch.cuda.is_available() else "cpu"


model, preprocess = ja_clip.load("rinna/japanese-clip-vit-b-16", cache_dir="/tmp/japanese_clip", device=device)
tokenizer = ja_clip.load_tokenizer()

img = Image.open(io.BytesIO(requests.get('https://images.pexels.com/photos/2253275/pexels-photo-2253275.jpeg?auto=compress&cs=tinysrgb&dpr=3&h=750&w=1260').content))
image = preprocess(img).unsqueeze(0).to(device)
encodings = ja_clip.tokenize(
    texts=["犬", "猫", "象"],
    max_seq_len=77,
    device=device,
    tokenizer=tokenizer, # this is optional. if you don't pass, load tokenizer each time
)

with torch.no_grad():
    image_features = model.get_image_features(image)
    text_features = model.get_text_features(**encodings)
    
    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)

print("Label probs:", text_probs)  # prints: [[1.0, 0.0, 0.0]]

Model architecture

The model was trained a ViT-B/16 Transformer architecture as an image encoder and uses a 12-layer BERT as a text encoder. The image encoder was initialized from the AugReg vit-base-patch16-224 model.

Training

The model was trained on CC12M translated the captions to Japanese.

Release date

May 12, 2022

How to cite

@misc{rinna-japanese-clip-vit-b-16,
    title = {rinna/japanese-clip

Your obligations as a japanese clip vit b 16 deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Languages

Library