Kosmos 2 Patch14 224

🚀 Kosmos-2：将多模态大语言模型与现实世界相连接

Kosmos-2 是一款多模态大语言模型，它能够处理图像和文本信息，实现诸如多模态定位、多模态指称、感知语言任务和图像描述等功能。通过改变输入提示，模型可以执行不同的任务，为多模态交互提供了强大的支持。

注意事项

⚠️ 重要提示

此模型（Hub 上的远程代码）已弃用。请使用 https://huggingface.co/microsoft/kosmos-2-patch14-224。

在输入格式方面有一些变化，请参阅 https://huggingface.co/microsoft/kosmos-2-patch14-224 中的模型卡片。

示例图片

🚀 快速开始

此 Hub 仓库包含了来自微软的 原始 Kosmos-2 模型 的 HuggingFace transformers 实现。使用以下代码开始使用该模型：

import requests

from PIL import Image
from transformers import AutoProcessor, AutoModelForVision2Seq


model = AutoModelForVision2Seq.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)

prompt = "<grounding>An image of"

url = "https://huggingface.co/ydshieh/kosmos-2-patch14-224/resolve/main/snowman.png"
image = Image.open(requests.get(url, stream=True).raw)

# 原始的 Kosmos-2 演示会先保存图像，然后重新加载它。对于某些图像，这会导致略微不同的图像输入，并改变生成输出。
# 如果您想匹配原始演示的输出，请取消注释以下 2 行。
# （演示中的 `two_dogs.jpg` 就是一个例子）
# image.save("new_image.jpg")
# image = Image.open("new_image.jpg")

inputs = processor(text=prompt, images=image, return_tensors="pt")

generated_ids = model.generate(
    pixel_values=inputs["pixel_values"],
    input_ids=inputs["input_ids"][:, :-1],
    attention_mask=inputs["attention_mask"][:, :-1],
    img_features=None,
    img_attn_mask=inputs["img_attn_mask"][:, :-1],
    use_cache=True,
    max_new_tokens=64,
)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

# 指定 `cleanup_and_extract=False` 以查看原始的模型生成结果。
processed_text = processor.post_process_generation(generated_text, cleanup_and_extract=False)

print(processed_text)
# `<grounding> An image of<phrase> a snowman</phrase><object><patch_index_0044><patch_index_0863></object> warming himself by<phrase> a fire</phrase><object><patch_index_0005><patch_index_0911></object>.`

# 默认情况下，生成的文本会被清理，实体也会被提取。
processed_text, entities = processor.post_process_generation(generated_text)

print(processed_text)
# `An image of a snowman warming himself by a fire.`

print(entities)
# `[('a snowman', (12, 21), [(0.390625, 0.046875, 0.984375, 0.828125)]), ('a fire', (41, 47), [(0.171875, 0.015625, 0.484375, 0.890625)])]`

💻 使用示例

基础用法

在图像上绘制实体的边界框

import cv2
import numpy as np
import os
import requests
import torch
import torchvision.transforms as T

from PIL import Image


def is_overlapping(rect1, rect2):
    x1, y1, x2, y2 = rect1
    x3, y3, x4, y4 = rect2
    return not (x2 < x3 or x1 > x4 or y2 < y3 or y1 > y4)


def draw_entity_boxes_on_image(image, entities, show=False, save_path=None):
    """_summary_
    Args:
        image (_type_): 图像或图像路径
        collect_entity_location (_type_): _description_
    """
    if isinstance(image, Image.Image):
        image_h = image.height
        image_w = image.width
        image = np.array(image)[:, :, [2, 1, 0]]
    elif isinstance(image, str):
        if os.path.exists(image):
            pil_img = Image.open(image).convert("RGB")
            image = np.array(pil_img)[:, :, [2, 1, 0]]
            image_h = pil_img.height
            image_w = pil_img.width
        else:
            raise ValueError(f"无效的图像路径，{image}")
    elif isinstance(image, torch.Tensor):
        # pdb.set_trace()
        image_tensor = image.cpu()
        reverse_norm_mean = torch.tensor([0.48145466, 0.4578275, 0.40821073])[:, None, None]
        reverse_norm_std = torch.tensor([0.26862954, 0.26130258, 0.27577711])[:, None, None]
        image_tensor = image_tensor * reverse_norm_std + reverse_norm_mean
        pil_img = T.ToPILImage()(image_tensor)
        image_h = pil_img.height
        image_w = pil_img.width
        image = np.array(pil_img)[:, :, [2, 1, 0]]
    else:
        raise ValueError(f"无效的图像格式，{type(image)} 对应于 {image}")

    if len(entities) == 0:
        return image

    new_image = image.copy()
    previous_bboxes = []
    # 文本大小
    text_size = 1
    # 文本粗细
    text_line = 1  # int(max(1 * min(image_h, image_w) / 512, 1))
    box_line = 3
    (c_width, text_height), _ = cv2.getTextSize("F", cv2.FONT_HERSHEY_COMPLEX, text_size, text_line)
    base_height = int(text_height * 0.675)
    text_offset_original = text_height - base_height
    text_spaces = 3

    for entity_name, (start, end), bboxes in entities:
        for (x1_norm, y1_norm, x2_norm, y2_norm) in bboxes:
            orig_x1, orig_y1, orig_x2, orig_y2 = int(x1_norm * image_w), int(y1_norm * image_h), int(x2_norm * image_w), int(y2_norm * image_h)
            # 绘制边界框
            # 随机颜色
            color = tuple(np.random.randint(0, 255, size=3).tolist())
            new_image = cv2.rectangle(new_image, (orig_x1, orig_y1), (orig_x2, orig_y2), color, box_line)

            l_o, r_o = box_line // 2 + box_line % 2, box_line // 2 + box_line % 2 + 1

            x1 = orig_x1 - l_o
            y1 = orig_y1 - l_o

            if y1 < text_height + text_offset_original + 2 * text_spaces:
                y1 = orig_y1 + r_o + text_height + text_offset_original + 2 * text_spaces
                x1 = orig_x1 + r_o

            # 添加文本背景
            (text_width, text_height), _ = cv2.getTextSize(f"  {entity_name}", cv2.FONT_HERSHEY_COMPLEX, text_size, text_line)
            text_bg_x1, text_bg_y1, text_bg_x2, text_bg_y2 = x1, y1 - (text_height + text_offset_original + 2 * text_spaces), x1 + text_width, y1

            for prev_bbox in previous_bboxes:
                while is_overlapping((text_bg_x1, text_bg_y1, text_bg_x2, text_bg_y2), prev_bbox):
                    text_bg_y1 += (text_height + text_offset_original + 2 * text_spaces)
                    text_bg_y2 += (text_height + text_offset_original + 2 * text_spaces)
                    y1 += (text_height + text_offset_original + 2 * text_spaces)

                    if text_bg_y2 >= image_h:
                        text_bg_y1 = max(0, image_h - (text_height + text_offset_original + 2 * text_spaces))
                        text_bg_y2 = image_h
                        y1 = image_h
                        break

            alpha = 0.5
            for i in range(text_bg_y1, text_bg_y2):
                for j in range(text_bg_x1, text_bg_x2):
                    if i < image_h and j < image_w:
                        if j < text_bg_x1 + 1.35 * c_width:
                            # 原始颜色
                            bg_color = color
                        else:
                            # 白色
                            bg_color = [255, 255, 255]
                        new_image[i, j] = (alpha * new_image[i, j] + (1 - alpha) * np.array(bg_color)).astype(np.uint8)

            cv2.putText(
                new_image, f"  {entity_name}", (x1, y1 - text_offset_original - 1 * text_spaces), cv2.FONT_HERSHEY_COMPLEX, text_size, (0, 0, 0), text_line, cv2.LINE_AA
            )
            # previous_locations.append((x1, y1))
            previous_bboxes.append((text_bg_x1, text_bg_y1, text_bg_x2, text_bg_y2))

    pil_image = Image.fromarray(new_image[:, :, [2, 1, 0]])
    if save_path:
        pil_image.save(save_path)
    if show:
        pil_image.show()

    return new_image


# （与上一个代码示例中的图像相同）
url = "https://huggingface.co/ydshieh/kosmos-2-patch14-224/resolve/main/snowman.jpg"
image = Image.open(requests.get(url, stream=True).raw)

# 从上一个代码示例中获取
entities = [('a snowman', (12, 21), [(0.390625, 0.046875, 0.984375, 0.828125)]), ('a fire', (41, 47), [(0.171875, 0.015625, 0.484375, 0.890625)])]

# 绘制边界框
draw_entity_boxes_on_image(image, entities, show=True)

高级用法

通过改变提示执行不同任务

import requests

from PIL import Image
from transformers import AutoProcessor, AutoModelForVision2Seq


model = AutoModelForVision2Seq.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)

url = "https://huggingface.co/ydshieh/kosmos-2-patch14-224/resolve/main/snowman.png"
image = Image.open(requests.get(url, stream=True).raw)

def run_example(prompt):

    inputs = processor(text=prompt, images=image, return_tensors="pt")
    generated_ids = model.generate(
        pixel_values=inputs["pixel_values"],
        input_ids=inputs["input_ids"][:, :-1],
        attention_mask=inputs["attention_mask"][:, :-1],
        img_features=None,
        img_attn_mask=inputs["img_attn_mask"][:, :-1],
        use_cache=True,
        max_new_tokens=64,
    )
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
    _processed_text = processor.post_process_generation(generated_text, cleanup_and_extract=False)
    processed_text, entities = processor.post_process_generation(generated_text)
    print(processed_text)
    print(entities)
    print(_processed_text)

多模态定位

• 短语定位

prompt = "<grounding><phrase> a snowman</phrase>"
run_example(prompt)

# a snowman is warming himself by the fire
# [('a snowman', (0, 9), [(0.390625, 0.046875, 0.984375, 0.828125)]), ('the fire', (32, 40), [(0.203125, 0.015625, 0.453125, 0.859375)])]

# <grounding><phrase> a snowman</phrase><object><patch_index_0044><patch_index_0863></object> is warming himself by<phrase> the fire</phrase><object><patch_index_0006><patch_index_0878></object>

• 指代表达理解

prompt = "<grounding><phrase> a snowman next to a fire</phrase>"
run_example(prompt)

# a snowman next to a fire
# [('a snowman next to a fire', (0, 24), [(0.390625, 0.046875, 0.984375, 0.828125)])]

# <grounding><phrase> a snowman next to a fire</phrase><object><patch_index_0044><patch_index_0863></object>

多模态指称

• 指代表达生成

prompt = "<grounding><phrase> It</phrase><object><patch_index_0044><patch_index_0863></object> is"
run_example(prompt)

# It is snowman in a hat and scarf
# [('It', (0, 2), [(0.390625, 0.046875, 0.984375, 0.828125)])]

# <grounding><phrase> It</phrase><object><patch_index_0044><patch_index_0863></object> is snowman in a hat and scarf

感知语言任务

• 定位视觉问答

prompt = "<grounding> Question: What is special about this image? Answer:"
run_example(prompt)

# Question: What is special about this image? Answer: The image features a snowman sitting by a campfire in the snow.
# [('a snowman', (71, 80), [(0.390625, 0.046875, 0.984375, 0.828125)]), ('a campfire', (92, 102), [(0.109375, 0.640625, 0.546875, 0.984375)])]

# <grounding> Question: What is special about this image? Answer: The image features<phrase> a snowman</phrase><object><patch_index_0044><patch_index_0863></object> sitting by<phrase> a campfire</phrase><object><patch_index_0643><patch_index_1009></object> in the snow.

• 通过边界框进行多模态指称的定位视觉问答

prompt = "<grounding> Question: Where is<phrase> the fire</phrase><object><patch_index_0005><patch_index_0911></object> next to? Answer:"
run_example(prompt)

# Question: Where is the fire next to? Answer: Near the snowman.
# [('the fire', (19, 27), [(0.171875, 0.015625, 0.484375, 0.890625)]), ('the snowman', (50, 61), [(0.390625, 0.046875, 0.984375, 0.828125)])]

# <grounding> Question: Where is<phrase> the fire</phrase><object><patch_index_0005><patch_index_0911></object> next to? Answer: Near<phrase> the snowman</phrase><object><patch_index_0044><patch_index_0863></object>.

定位图像描述

• 简要描述

prompt = "<grounding> An image of"
run_example(prompt)

# An image of a snowman warming himself by a campfire.
# [('a snowman', (12, 21), [(0.390625, 0.046875, 0.984375, 0.828125)]), ('a campfire', (41, 51), [(0.109375, 0.640625, 0.546875, 0.984375)])]

# <grounding> An image of<phrase> a snowman</phrase><object><patch_index_0044><patch_index_0863></object> warming himself by<phrase> a campfire</phrase><object><patch_index_0643><patch_index_1009></object>.

• 详细描述

prompt = "<grounding> Describe this image in detail:"
run_example(prompt)

# Describe this image in detail: The image features a snowman sitting by a campfire in the snow. He is wearing a hat, scarf, and gloves, with a pot nearby and a cup
# [('a campfire', (71, 81), [(0.171875, 0.015625, 0.484375, 0.984375)]), ('a hat', (109, 114), [(0.515625, 0.046875, 0.828125, 0.234375)]), ('scarf', (116, 121), [(0.515625, 0.234375, 0.890625, 0.578125)]), ('gloves', (127, 133), [(0.515625, 0.390625, 0.640625, 0.515625)]), ('a pot', (140, 145), [(0.078125, 0.609375, 0.265625, 0.859375)])]

# <grounding> Describe this image in detail: The image features a snowman sitting by<phrase> a campfire</phrase><object><patch_index_0005><patch_index_1007></object> in the snow. He is wearing<phrase> a hat</phrase><object><patch_index_0048><patch_index_0250></object>,<phrase> scarf</phrase><object><patch_index_0240><patch_index_0604></object>, and<phrase> gloves</phrase><object><patch_index_0400><patch_index_0532></object>, with<phrase> a pot</phrase><object><patch_index_0610><patch_index_0872></object> nearby and<phrase> a cup</phrase><object>

运行 Flask 服务器

flask_kosmos2.py 展示了该模型的 Flask 服务器实现，它允许将模型作为 REST API 进行访问。

启动服务器后，您可以向 http://localhost:8005/process_prompt 发送 POST 请求，并附带以下表单数据：

• prompt：例如 <grounding> an image of
• image：图像文件的二进制数据

这将产生一个包含以下 JSON 格式的回复：

• message：Kosmos-2 生成的文本
• entities：提取的实体

通过像 Postman 这样的应用程序可以轻松测试此功能。确保将图像字段设置为 File。

from PIL import Image
from transformers import AutoProcessor, AutoModelForVision2Seq
from flask import Flask, request, jsonify
import json

app = Flask(__name__)

model = AutoModelForVision2Seq.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)


@app.route('/process_prompt', methods=['POST'])
def process_prompt():
    try:
        # 从 POST 请求中获取上传的图像数据
        uploaded_file = request.files['image']
        prompt = request.form.get('prompt')
        image = Image.open(uploaded_file.stream)

        print(image.size)

        inputs = processor(text=prompt, images=image, return_tensors="pt")

        generated_ids = model.generate(
            pixel_values=inputs["pixel_values"],
            input_ids=inputs["input_ids"][:, :-1],
            attention_mask=inputs["attention_mask"][:, :-1],
            img_features=None,
            img_attn_mask=inputs["img_attn_mask"][:, :-1],
            use_cache=True,
            max_new_tokens=64,
        )
        generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

        # 默认情况下，生成的文本会被清理，实体也会被提取。
        processed_text, entities = processor.post_process_generation(generated_text)
        parsed_entities = entities_to_json(entities)
        print(generated_text)
        print(processed_text)
        return jsonify({"message": processed_text, 'entities': parsed_entities})
    except Exception as e:
        return jsonify({"error": str(e)})


def entities_to_json(entities):
    result = []
    for e in entities:
        label = e[0]
        box_coords = e[1]
        box_size = e[2][0]
        entity_result = {
            "label": label,
            "boundingBoxPosition": {"x": box_coords[0], "y": box_coords[1]},
            "boundingBox": {"x_min": box_size[0], "y_min": box_size[1], "x_max": box_size[2], "y_max": box_size[3]}
        }
        print(entity_result)
        result.append(entity_result)

    return result


if __name__ == '__main__':
    app.run(host='localhost', port=8005)