《书生·浦语大模型实战营》第6课 学习笔记：Lagent & AgentLego 智能体应用搭建

def train():
 ...
 return 'Hello World'

mkdir -p /root/agent

studio-conda -t agent -o pytorch-2.1.2

conda create -n agent
conda activate agent
conda install python=3.10
conda install pytorch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 pytorch-cuda=11.8 -c pytorch -c nvidia

cd /root/agent
conda activate agent
git clone https://gitee.com/internlm/lagent.git
cd lagent && git checkout 581d9fb && pip install -e . && cd ..
git clone https://gitee.com/internlm/agentlego.git
cd agentlego && git checkout 7769e0d && pip install -e . && cd ..

conda activate agent
pip install lmdeploy==0.3.0

cd /root/agent
git clone -b camp2 https://gitee.com/internlm/Tutorial.git

cd /root/agent
wget http://download.openmmlab.com/agentlego/road.jpg

conda activate agent
pip install openmim==0.3.9
mim install mmdet==3.3.0

import re

import cv2
from agentlego.apis import load_tool

# load tool
tool = load_tool('ObjectDetection', device='cuda')

# apply tool
visualization = tool('/root/agent/road.jpg')
print(visualization)

# visualize
image = cv2.imread('/root/agent/road.jpg')

preds = visualization.split('\n')
pattern = r'(\w+) \((\d+), (\d+), (\d+), (\d+)\), score (\d+)'

for pred in preds:
    name, x1, y1, x2, y2, score = re.match(pattern, pred).groups()
    x1, y1, x2, y2, score = int(x1), int(y1), int(x2), int(y2), int(score)
    cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 1)
    cv2.putText(image, f'{name} {score}', (x1, y1), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 1)

cv2.imwrite('/root/agent/road_detection_direct.jpg', image)

/root/agent
├── agentlego
│   ├── agentlego
│   ├── docs
│   ├── examples
│   ├── LICENSE
│   └── ...
├── lagent
│   ├── docs
│   ├── examples
│   ├── lagent
│   ├── LICENSE
│   └── ...
├── Tutorial
│   ├── assets
│   ├── agent
│   ├── helloword
│   ├── huixiangdou
│   └── ...
├── direct_use.py
└── road.jpg

python direct_use.py 
Loads checkpoint by http backend from path: https://download.openmmlab.com/mmdetection/v3.0/rtmdet/rtmdet_l_8xb32-300e_coco/rtmdet_l_8xb32-300e_coco_20220719_112030-5a0be7c4.pth
Downloading: "https://download.openmmlab.com/mmdetection/v3.0/rtmdet/rtmdet_l_8xb32-300e_coco/rtmdet_l_8xb32-300e_coco_20220719_112030-5a0be7c4.pth" to /root/.cache/torch/hub/checkpoints/rtmdet_l_8xb32-300e_coco_20220719_112030-5a0be7c4.pth
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 433M/433M [00:58<00:00, 7.81MB/s]
The model and loaded state dict do not match exactly

unexpected key in source state_dict: data_preprocessor.mean, data_preprocessor.std

06/25 23:59:42 - mmengine - WARNING - Failed to search registry with scope "mmdet" in the "function" registry tree. As a workaround, the current "function" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmdet" is a correct scope, or whether the registry is initialized.
/root/.conda/envs/agent/lib/python3.10/site-packages/mmengine/visualization/visualizer.py:196: UserWarning: Failed to add <class 'mmengine.visualization.vis_backend.LocalVisBackend'>, please provide the `save_dir` argument.
  warnings.warn(f'Failed to add {vis_backend.__class__}, '
/root/.conda/envs/agent/lib/python3.10/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at 
/opt/conda/conda-bld/pytorch_1702400410390/work/aten/src/ATen/native/TensorShape.cpp:3526.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
Inference ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━   
truck (345, 428, 528, 599), score 83
car (771, 510, 837, 565), score 81
car (604, 518, 677, 569), score 75
person (866, 503, 905, 595), score 74
person (287, 513, 320, 596), score 74
person (964, 501, 999, 604), score 72
person (1009, 503, 1047, 602), score 69
person (259, 510, 279, 575), score 65
car (1074, 524, 1275, 691), score 64
person (993, 508, 1016, 597), score 62
truck (689, 483, 764, 561), score 62
bicycle (873, 551, 903, 602), score 60
person (680, 523, 699, 567), score 55
bicycle (968, 551, 996, 609), score 53
bus (826, 482, 930, 560), score 52
bicycle (1011, 551, 1043, 617), score 51
(agent) root@intern-studio-50001213:~/agent# 

def llm_internlm2_lmdeploy(cfg):
    url = cfg['url'].strip()
    llm = LMDeployClient(
-         model_name='internlm2-chat-20b',
+         model_name='internlm2-chat-7b',
        url=url,
        meta_template=INTERNLM2_META,
        top_p=0.8,
        top_k=100,
        temperature=cfg.get('temperature', 0.7),
        repetition_penalty=1.0,
        stop_words=['<|im_end|>'])
    return llm

conda activate agent
lmdeploy serve api_server /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-7b \
                            --server-name 127.0.0.1 \
                            --model-name internlm2-chat-7b \
                            --cache-max-entry-count 0.1

conda activate agent
cd /root/agent/agentlego/webui
python one_click.py

ssh -CNg -L 7860:127.0.0.1:7860 -L 23333:127.0.0.1:23333 root@ssh.intern-ai.org.cn -p 你的 ssh 端口号

import json
import requests

import numpy as np

from agentlego.types import Annotated, ImageIO, Info
from agentlego.utils import require
from .base import BaseTool


class MagicMakerImageGeneration(BaseTool):

    default_desc = ('This tool can call the api of magicmaker to '
                    'generate an image according to the given keywords.')

    styles_option = [
        'dongman',  # 动漫
        'guofeng',  # 国风
        'xieshi',   # 写实
        'youhua',   # 油画
        'manghe',   # 盲盒
    ]
    aspect_ratio_options = [
        '16:9', '4:3', '3:2', '1:1',
        '2:3', '3:4', '9:16'
    ]

    @require('opencv-python')
    def __init__(self,
                 style='guofeng',
                 aspect_ratio='4:3'):
        super().__init__()
        if style in self.styles_option:
            self.style = style
        else:
            raise ValueError(f'The style must be one of {self.styles_option}')
        
        if aspect_ratio in self.aspect_ratio_options:
            self.aspect_ratio = aspect_ratio
        else:
            raise ValueError(f'The aspect ratio must be one of {aspect_ratio}')

    def apply(self,
              keywords: Annotated[str,
                                  Info('A series of Chinese keywords separated by comma.')]
        ) -> ImageIO:
        import cv2
        response = requests.post(
            url='https://magicmaker.openxlab.org.cn/gw/edit-anything/api/v1/bff/sd/generate',
            data=json.dumps({
                "official": True,
                "prompt": keywords,
                "style": self.style,
                "poseT": False,
                "aspectRatio": self.aspect_ratio
            }),
            headers={'content-type': 'application/json'}
        )
        image_url = response.json()['data']['imgUrl']
        image_response = requests.get(image_url)
        image = cv2.cvtColor(cv2.imdecode(np.frombuffer(image_response.content, np.uint8), cv2.IMREAD_COLOR),cv2.COLOR_BGR2RGB)
        return ImageIO(image)

from .base import BaseTool
from .calculator import Calculator
from .func import make_tool
from .image_canny import CannyTextToImage, ImageToCanny
from .image_depth import DepthTextToImage, ImageToDepth
from .image_editing import ImageExpansion, ImageStylization, ObjectRemove, ObjectReplace
from .image_pose import HumanBodyPose, HumanFaceLandmark, PoseToImage
from .image_scribble import ImageToScribble, ScribbleTextToImage
from .image_text import ImageDescription, TextToImage
from .imagebind import AudioImageToImage, AudioTextToImage, AudioToImage, ThermalToImage
from .object_detection import ObjectDetection, TextToBbox
from .ocr import OCR
from .scholar import *  # noqa: F401, F403
from .search import BingSearch, GoogleSearch
from .segmentation import SegmentAnything, SegmentObject, SemanticSegmentation
from .speech_text import SpeechToText, TextToSpeech
from .translation import Translation
from .vqa import VQA
+ from .magicmaker_image_generation import MagicMakerImageGeneration

__all__ = [
    'CannyTextToImage', 'ImageToCanny', 'DepthTextToImage', 'ImageToDepth',
    'ImageExpansion', 'ObjectRemove', 'ObjectReplace', 'HumanFaceLandmark',
    'HumanBodyPose', 'PoseToImage', 'ImageToScribble', 'ScribbleTextToImage',
    'ImageDescription', 'TextToImage', 'VQA', 'ObjectDetection', 'TextToBbox', 'OCR',
    'SegmentObject', 'SegmentAnything', 'SemanticSegmentation', 'ImageStylization',
    'AudioToImage', 'ThermalToImage', 'AudioImageToImage', 'AudioTextToImage',
    'SpeechToText', 'TextToSpeech', 'Translation', 'GoogleSearch', 'Calculator',
-     'BaseTool', 'make_tool', 'BingSearch'
+     'BaseTool', 'make_tool', 'BingSearch', 'MagicMakerImageGeneration'
]

conda activate agent
lmdeploy serve api_server /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-7b \
                            --server-name 127.0.0.1 \
                            --model-name internlm2-chat-7b \
                            --cache-max-entry-count 0.1

conda activate agent
cd /root/agent/agentlego/webui
python one_click.py

ssh -CNg -L 7860:127.0.0.1:7860 -L 23333:127.0.0.1:23333 root@ssh.intern-ai.org.cn -p 你的 ssh 端口号

import cv2

name = 'person'
x1,y1,x2,y2 = 556, 528, 770, 902
score =  83

image_path = r'D:\code\c++\myyolo\opencv_utils\people.png'

image_test = cv2.imread(image_path)

cv2.rectangle(image_test, (x1, y1), (x2, y2), (0, 255, 0), 1)
cv2.putText(image_test, f'{name} {score}', (x1, y1), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 1)

cv2.imshow('plot_result',image_test)
cv2.waitKey(0)