Yolo11x_FM30k_Event_withcaption / app-com_sentenca.py
pedrororo's picture
Upload 2 files
aa3bb8e verified
import cv2
import gradio as gr
from ultralytics import YOLO
# Load the model once globally
MODEL_PATH = "best.pt"
model = YOLO(MODEL_PATH)
def detect_and_visualize(image):
# image is a NumPy array from Gradio
# Perform inference directly on this array
results = model(image)
# Ensure image is in the correct color space (most likely already RGB)
annotated_image = image.copy()
detections = []
for result in results:
boxes = result.boxes.xyxy.cpu().numpy()
confidences = result.boxes.conf.cpu().numpy()
class_ids = result.boxes.cls.cpu().numpy().astype(int)
for box, confidence, class_id in zip(boxes, confidences, class_ids):
x_min, y_min, x_max, y_max = map(int, box)
class_name = model.names[class_id]
# Pick a color or use a fixed color, no need for random if not desired
color = (0, 255, 0)
cv2.rectangle(annotated_image, (x_min, y_min), (x_max, y_max), color, 2)
label = f"{class_name} {confidence:.2f}"
cv2.putText(annotated_image, label, (x_min, y_min - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
detections.append({
"label": class_name,
"confidence": float(confidence),
"bounding_box": {
"x1": x_min,
"y1": y_min,
"x2": x_max,
"y2": y_max
}
})
return annotated_image, detections
def gradio_interface(image):
annotated_image, detections = detect_and_visualize(image)
return annotated_image, detections
interface = gr.Interface(
fn=gradio_interface,
inputs=gr.Image(type="numpy", label="Upload Image"),
outputs=[
gr.Image(type="numpy", label="Annotated Image"),
gr.JSON(label="Detection Details")
],
title="YOLO Object Detection",
description="Upload an image to detect objects and view annotated results along with detailed detection data."
)
if __name__ == "__main__":
interface.launch()