我又一个python文件，名为grounding_dino_demo.py，其代码为：
from groundingdino.util.inference import load_model, load_image, predict, annotate, Model
import cv2
CONFIG_PATH = "GroundingDINO/groundingdino/config/GroundingDINO_SwinT_OGC.py"
CHECKPOINT_PATH = "./groundingdino_swint_ogc.pth"
DEVICE = "cuda"
IMAGE_PATH = "assets/demo7.jpg"
TEXT_PROMPT = "Horse. Clouds. Grasses. Sky. Hill."
BOX_TRESHOLD = 0.35
TEXT_TRESHOLD = 0.25
image_source, image = load_image(IMAGE_PATH)
model = load_model(CONFIG_PATH, CHECKPOINT_PATH)
boxes, logits, phrases = predict(
model=model,
image=image,
caption=TEXT_PROMPT,
box_threshold=BOX_TRESHOLD,
text_threshold=TEXT_TRESHOLD,
device=DEVICE,
)
annotated_frame = annotate(image_source=image_source, boxes=boxes, logits=logits, phrases=phrases)
cv2.imwrite("annotated_image.jpg", annotated_frame)
当我在外部传参时：执行
python3 grounding_dino_demo.py --config GroundingDINO/groundingdino/config/GroundingDINO_SwinT_OGC.py --grounded_checkpoint groundingdino_swint_ogc.pth --input_image assets/xs_7.jpg --output_dir "outputs" --box_threshold 0.3 --text_threshold 0.25 --text_prompt "tomato"
标签：传参,load,python,image,--,PATH,groundingdino,方法,model From： https://www.cnblogs.com/chentiao/p/17600509.html