app.py

import gradio as gr
import supervision as sv
import numpy as np
import cv2
from inference import get_roboflow_model

# Define the Roboflow model
model = get_roboflow_model(model_id="people-detection-general/5", api_key="API_KEY")

def callback(image_slice: np.ndarray) -> sv.Detections:
    results = model.infer(image_slice)[0]
    return sv.Detections.from_inference(results)

# Define the slicer
slicer = sv.InferenceSlicer(callback=callback)

def detect_objects(image):
    image = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)  # Convert from RGB (Gradio) to BGR (OpenCV)
    
    # Run inference
    sliced_detections = slicer(image=image)

    # Annotating the image with boxes and labels
    label_annotator = sv.LabelAnnotator()
    box_annotator = sv.BoxAnnotator()

    annotated_image = box_annotator.annotate(scene=image.copy(), detections=sliced_detections)
    annotated_image = label_annotator.annotate(scene=annotated_image, detections=sliced_detections)

    # Count detected objects per class
    class_counts = {}
    for detection in sliced_detections:
        class_name = detection.class_name
        class_counts[class_name] = class_counts.get(class_name, 0) + 1

    # Total objects detected
    total_count = sum(class_counts.values())
    
    # Display results: annotated image and object counts
    result_image = cv2.cvtColor(annotated_image, cv2.COLOR_BGR2RGB)  # Convert back to RGB for Gradio
    return result_image, class_counts, total_count

# Create a Gradio interface
iface = gr.Interface(
    fn=detect_objects,
    inputs=gr.Image(type="pil"),
    outputs=[gr.Image(type="pil"), gr.JSON(), gr.Number(label="Total Objects Detected")],
    live=True
)

# Launch the Gradio interface
iface.launch()