GroundingDINO（一种开集目标检测算法）服务化，根据文本生成检测框

wget -q http://github.com/IDEA-Research/GroundingDINO/releases/download/v0.1.0-alpha/groundingdino_swint_ogc.pth

config.json
pytorch_model.bin
tokenizer_config.json
tokenizer.json
vocab.txt

FROM pytorch/pytorch:2.0.1-cuda11.7-cudnn8-devel
ARG DEBIAN_FRONTEND=noninteractive

#for Chinese User, uncomment this line
# COPY sources.list /etc/apt/sources.list

RUN apt update && \
     apt install openjdk-17-jdk -y

RUN apt install git -y

#install python packages
COPY requirements.txt /root/
RUN pip install -r /root/requirements.txt --no-cache -i http://repo.huaweicloud.com/repository/pypi/simple/

docker build -t torchserve:groundingdino .

docker run --rm -it -v $(pwd):/data -w /data torchserve:groundingdino bash -c "torch-model-archiver --model-name groundingdino --version 1.0 --serialized-file weights/groundingdino_swint_ogc.pth --handler grounding_dino_handler.py --extra-files GroundingDINO_SwinT_OGC.py,bert-base-uncased/*"

docker run -d --name groundingdino -v $(pwd)/model_store:/model_store -p 8080:8080 -p 8081:8081 -p 8082:8082 torchserve:groundingdino bash -c "torchserve --start --foreground --model-store /model_store --models groundingdino=groundingdino.mar"

import requests
import base64
import time
# URL for the web service
url = "http://ip:8080/predictions/groundingdino"
headers = {"Content-Type": "application/json"}

# Input data
with open("test.jpg", "rb") as f:
    image = f.read()

data = {
        "image": base64.b64encode(image).decode("utf-8"), # base64 encoded image or BytesIO
        "caption": "steel pipe", # text prompt, split by "." for multiple phrases
        "box_threshold": 0.25, # threshold for object detection
        "caption_threshold": 0.25 # threshold for text similarity
        }

# Make the request and display the response

resp = requests.post(url=url, headers=headers, json=data)
outputs = resp.json()
'''
the outputs will be like:
    {
        "boxes": [[0.0, 0.0, 1.0, 1.0]], # list of bounding boxes in xyxy format
        "scores": [0.9999998807907104], # list of object detection scores
        "phrases": ["steel pipe"] # list of text phrases
    }

'''