japanese clip
v0.2.0

Dieses Repository enthält Codes für japanische Clip-Varianten (kontrastive Sprachbild-Pre-Training) von Rinna Co., Ltd.
| Inhaltsverzeichnis |
|---|
| Nachricht |
| Vorbereitete Modelle |
| Verwendung |
| Zitat |
| Lizenz |
v0.2.0 wurde veröffentlicht!
rinna/japanese-cloob-vit-b-16 54,64.scripts/example.py ) für die Klassifizierung von Null-Shot-Imagnet. Diese Vorlagen wurden für Japanisch aufgrund der OpenAI 80 -Vorlagen gereinigt.| Modellname | Top1* | Top5* |
|---|---|---|
| Rinna/Japanisch-Cloob-Vit-B-16 | 54.64 | 72,86 |
| Rinna/Japanisch-Clip-Vit-B-16 | 50.69 | 72.35 |
| Sonoisa/Clip-Vit-B-32-Japanese-V1 | 38,88 | 60.71 |
| Mehrsprachiger Clip | 14.36 | 27.28 |
*Null-Shot ImageNet-Validierungsgenauigkeit Setzen Sie die Top-K-Genauigkeit.
$ pip install git+https://github.com/rinnakk/japanese-clip.git from PIL import Image
import torch
import japanese_clip as ja_clip
device = "cuda" if torch . cuda . is_available () else "cpu"
# ja_clip.available_models()
# ['rinna/japanese-clip-vit-b-16', 'rinna/japanese-cloob-vit-b-16']
# If you want v0.1.0 models, set `revision='v0.1.0'`
model , preprocess = ja_clip . load ( "rinna/japanese-clip-vit-b-16" , cache_dir = "/tmp/japanese_clip" , device = device )
tokenizer = ja_clip . load_tokenizer ()
image = preprocess ( Image . open ( "./data/dog.jpeg" )). 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]] So zitieren Sie dieses Repository:
@inproceedings{japanese-clip,
author = {シーン 誠, 趙 天雨, 沢田 慶},
title = {日本語における言語画像事前学習モデルの構築と公開},
booktitle= {The 25th Meeting on Image Recognition and Understanding},
year = 2022,
month = July,
}Die Apache 2.0 -Lizenz