Clip Vit Base Patch32 Ko

🚀 clip-vit-base-patch32-ko

这是一个韩语CLIP模型，通过Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation进行训练，可用于图像分类等任务。

🚀 快速开始

本模型可快速用于图像分类任务，以下是使用示例。

📦 安装指南

文档未提及具体安装步骤，可参考模型仓库相关说明进行安装。

💻 使用示例

基础用法

import requests
import torch
from PIL import Image
from transformers import AutoModel, AutoProcessor

repo = "Bingsu/clip-vit-base-patch32-ko"
model = AutoModel.from_pretrained(repo)
processor = AutoProcessor.from_pretrained(repo)

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(text=["고양이 두 마리", "개 두 마리"], images=image, return_tensors="pt", padding=True)
with torch.inference_mode():
    outputs = model(**inputs)
logits_per_image = outputs.logits_per_image
probs = logits_per_image.softmax(dim=1)

>>> probs
tensor([[0.9926, 0.0074]])

高级用法

from transformers import pipeline

repo = "Bingsu/clip-vit-base-patch32-ko"
pipe = pipeline("zero-shot-image-classification", model=repo)

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
result = pipe(images=url, candidate_labels=["고양이 한 마리", "고양이 두 마리", "분홍색 소파에 드러누운 고양이 친구들"], hypothesis_template="{}")

>>> result
[{'score': 0.9456236958503723, 'label': '분홍색 소파에 드러누운 고양이 친구들'},
 {'score': 0.05315302312374115, 'label': '고양이 두 마리'},
 {'score': 0.0012233294546604156, 'label': '고양이 한 마리'}]

📚 详细文档

Tokenizer

分词器是将韩语数据和英语数据按7:3的比例混合，通过原CLIP分词器的.train_new_from_iterator方法训练得到的。

参考代码：https://github.com/huggingface/transformers/blob/bc21aaca789f1a366c05e8b5e111632944886393/src/transformers/models/clip/modeling_clip.py#L661-L666

        # text_embeds.shape = [batch_size, sequence_length, transformer.width]
        # take features from the eot embedding (eot_token is the highest number in each sequence)
        # casting to torch.int for onnx compatibility: argmax doesn't support int64 inputs with opset 14
        pooled_output = last_hidden_state[
            torch.arange(last_hidden_state.shape[0]), input_ids.to(torch.int).argmax(dim=-1)
        ]

由于CLIP模型在计算pooled_output时使用id最大的标记，因此eos标记必须是最后一个标记。

📄 许可证

本项目采用MIT许可证。