|
|
import gradio as gr |
|
|
from transformers import DetrImageProcessor, DetrForObjectDetection |
|
|
import torch |
|
|
from PIL import Image, ImageDraw |
|
|
|
|
|
|
|
|
model_name = "facebook/detr-resnet-50" |
|
|
processor = DetrImageProcessor.from_pretrained(model_name) |
|
|
model = DetrForObjectDetection.from_pretrained(model_name) |
|
|
|
|
|
|
|
|
def detect_objects(image): |
|
|
|
|
|
inputs = processor(images=image, return_tensors="pt") |
|
|
outputs = model(**inputs) |
|
|
|
|
|
|
|
|
target_sizes = torch.tensor([image.size[::-1]]) |
|
|
results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.5)[0] |
|
|
|
|
|
draw = ImageDraw.Draw(image) |
|
|
boxes_info = [] |
|
|
|
|
|
for score, label, box in zip(results["scores"], results["labels"], results["boxes"]): |
|
|
box = [round(i, 2) for i in box.tolist()] |
|
|
draw.rectangle(box, outline="red", width=3) |
|
|
boxes_info.append({ |
|
|
"box": box, |
|
|
"label": model.config.id2label[label.item()], |
|
|
"score": round(score.item(), 3) |
|
|
}) |
|
|
|
|
|
return image, boxes_info |
|
|
|
|
|
|
|
|
with gr.Blocks() as demo: |
|
|
img_input = gr.Image(type="pil") |
|
|
output_img = gr.Image(type="pil") |
|
|
output_info = gr.JSON() |
|
|
|
|
|
btn = gr.Button("ตรวจจับอวัยวะ") |
|
|
btn.click(detect_objects, inputs=img_input, outputs=[output_img, output_info]) |
|
|
|
|
|
demo.launch() |
