许可证：MIT
语言：

• 中文
  标签：
• GPT-2
• ViT

模型介绍

1. 使用ViT对图像进行编码，再通过GPT-2进行解码。
2. ViT模型采用google/vit-base-patch16-224，GPT-2采用yuanzhoulvpi/gpt2_chinese。
3. 本模型支持中文。

训练代码

GitHub链接

推理代码

from transformers import (VisionEncoderDecoderModel,   
                          AutoTokenizer, ViTImageProcessor)  
import torch  
from PIL import Image  

vision_encoder_decoder_model_name_or_path = "yuanzhoulvpi/vit-gpt2-image-chinese-captioning"  
processor = ViTImageProcessor.from_pretrained(vision_encoder_decoder_model_name_or_path)  
tokenizer = AutoTokenizer.from_pretrained(vision_encoder_decoder_model_name_or_path)  
model = VisionEncoderDecoderModel.from_pretrained(vision_encoder_decoder_model_name_or_path)  
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")  
model.to(device)  

max_length = 16  
num_beams = 4  
gen_kwargs = {"max_length": max_length, "num_beams": num_beams}  

def predict_step(image_paths):  
    images = []  
    for image_path in image_paths:  
        i_image = Image.open(image_path)  
        if i_image.mode != "RGB":  
            i_image = i_image.convert(mode="RGB")  
        images.append(i_image)  

    pixel_values = processor(images=images, return_tensors="pt").pixel_values  
    pixel_values = pixel_values.to(device)  

    output_ids = model.generate(pixel_values, **gen_kwargs)  

    preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)  
    preds = [pred.strip() for pred in preds]  
    return preds  

predict_step(['bigdata/image_data/train-1000200.jpg'])  

效果示例

示例1

示例2