Nano Image Captioning

🚀 纳米图像字幕生成模型

这是一个基于BERT-Tiny和ViT-Tiny的图像字幕生成模型，仅40MB！它在CPU上也能快速运行，为图像添加描述信息提供了高效解决方案。

🚀 快速开始

此图像字幕生成模型能快速为图像生成描述。以下是使用该模型的步骤：

from transformers import AutoTokenizer, AutoImageProcessor, VisionEncoderDecoderModel
import requests, time
from PIL import Image

model_path = "cnmoro/nano-image-captioning"

# 加载图像字幕生成模型以及对应的分词器和图像处理器
model = VisionEncoderDecoderModel.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)
image_processor = AutoImageProcessor.from_pretrained(model_path)

# 预处理图像
url = "https://upload.wikimedia.org/wikipedia/commons/thumb/4/47/New_york_times_square-terabass.jpg/800px-New_york_times_square-terabass.jpg"
image = Image.open(requests.get(url, stream=True).raw)
pixel_values = image_processor(image, return_tensors="pt").pixel_values

start = time.time()

# 生成字幕 - 建议设置
generated_ids = model.generate(
    pixel_values,
    temperature=0.7,
    top_p=0.8,
    top_k=50,
    num_beams=3 # 你可以使用1以实现更快的推理，但质量会略有下降
)
generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

end = time.time()

print(generated_text)
# a group of people are in the middle of a city.

print(f"Time taken: {end - start} seconds")
# Time taken: 0.07550048828125 seconds
# on CPU !

💻 使用示例

基础用法

from transformers import AutoTokenizer, AutoImageProcessor, VisionEncoderDecoderModel
import requests, time
from PIL import Image

model_path = "cnmoro/nano-image-captioning"

# 加载图像字幕生成模型以及对应的分词器和图像处理器
model = VisionEncoderDecoderModel.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)
image_processor = AutoImageProcessor.from_pretrained(model_path)

# 预处理图像
url = "https://upload.wikimedia.org/wikipedia/commons/thumb/4/47/New_york_times_square-terabass.jpg/800px-New_york_times_square-terabass.jpg"
image = Image.open(requests.get(url, stream=True).raw)
pixel_values = image_processor(image, return_tensors="pt").pixel_values

start = time.time()

# 生成字幕 - 建议设置
generated_ids = model.generate(
    pixel_values,
    temperature=0.7,
    top_p=0.8,
    top_k=50,
    num_beams=3 # 你可以使用1以实现更快的推理，但质量会略有下降
)
generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

end = time.time()

print(generated_text)
# a group of people are in the middle of a city.

print(f"Time taken: {end - start} seconds")
# Time taken: 0.07550048828125 seconds
# on CPU !

高级用法

# 如果你需要在多个图像上进行批量处理，可以将图像URL存储在列表中，然后循环处理每个图像。
from transformers import AutoTokenizer, AutoImageProcessor, VisionEncoderDecoderModel
import requests, time
from PIL import Image

model_path = "cnmoro/nano-image-captioning"

# 加载图像字幕生成模型以及对应的分词器和图像处理器
model = VisionEncoderDecoderModel.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)
image_processor = AutoImageProcessor.from_pretrained(model_path)

image_urls = [
    "https://upload.wikimedia.org/wikipedia/commons/thumb/4/47/New_york_times_square-terabass.jpg/800px-New_york_times_square-terabass.jpg",
    "https://example.com/another_image.jpg"
]

for url in image_urls:
    image = Image.open(requests.get(url, stream=True).raw)
    pixel_values = image_processor(image, return_tensors="pt").pixel_values

    start = time.time()

    # 生成字幕 - 建议设置
    generated_ids = model.generate(
        pixel_values,
        temperature=0.7,
        top_p=0.8,
        top_k=50,
        num_beams=3 # 你可以使用1以实现更快的推理，但质量会略有下降
    )
    generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

    end = time.time()

    print(generated_text)
    print(f"Time taken: {end - start} seconds")

📄 许可证

本项目采用Apache-2.0许可证。

📚 详细文档