app.py

import gradio as gr
import numpy as np
import cv2
import supervision as sv
from roboflow import Roboflow
import tempfile
import os
import requests
from dotenv import load_dotenv

# Load environment variables from .env file
load_dotenv()
api_key = os.getenv("ROBOFLOW_API_KEY")
workspace = os.getenv("ROBOFLOW_WORKSPACE")
project_name = os.getenv("ROBOFLOW_PROJECT")
model_version = int(os.getenv("ROBOFLOW_MODEL_VERSION"))

# Initialize Roboflow with the API key
rf = Roboflow(api_key=api_key)
project = rf.workspace(workspace).project(project_name)
model = project.version(model_version).model

def detect_objects(image):
    # Save the uploaded image to a temporary file
    with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp_file:
        image.save(temp_file, format="JPEG")
        temp_file_path = temp_file.name
    
    try:
        # Perform inference on the uploaded image using the Roboflow model
        predictions = model.predict(temp_file_path, confidence=60, overlap=80).json()

        # Initialize Supervision annotations
        detections = []
        for prediction in predictions['predictions']:
            # Get bounding box and class for each prediction
            bbox = prediction['bbox']
            class_name = prediction['class']
            confidence = prediction['confidence']
            
            # Add detection to Supervision Detections list
            detections.append(
                sv.Detection(
                    x1=bbox[0],
                    y1=bbox[1],
                    x2=bbox[2],
                    y2=bbox[3],
                    confidence=confidence,
                    class_name=class_name
                )
            )

        # Convert detections to a Detections object for Supervision
        detections = sv.Detections(detections)

        # Annotate the image with bounding boxes and labels
        label_annotator = sv.LabelAnnotator()
        box_annotator = sv.BoxAnnotator()
        
        # Read the image back for OpenCV processing
        image_cv = cv2.imread(temp_file_path)
        annotated_image = box_annotator.annotate(scene=image_cv.copy(), detections=detections)
        annotated_image = label_annotator.annotate(scene=annotated_image, detections=detections)

        # Count detected objects per class
        class_count = {}
        total_count = 0

        for detection in detections:
            class_name = detection.class_name
            class_count[class_name] = class_count.get(class_name, 0) + 1
            total_count += 1

        # Prepare result text
        result_text = "Detected Objects:\n\n"
        for class_name, count in class_count.items():
            result_text += f"{class_name}: {count}\n"
        result_text += f"\nTotal objects detected: {total_count}"

        # Save the annotated image as output
        output_image_path = "/tmp/prediction.jpg"
        cv2.imwrite(output_image_path, annotated_image)

    except requests.exceptions.HTTPError as http_err:
        result_text = f"HTTP error occurred: {http_err}"
        output_image_path = temp_file_path  # Return original image on error
    except Exception as err:
        result_text = f"An error occurred: {err}"
        output_image_path = temp_file_path  # Return original image on error

    # Clean up by removing the temporary file
    os.remove(temp_file_path)
    
    return output_image_path, result_text

# Gradio interface
with gr.Blocks() as iface:
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(type="pil", label="Input Image")
        with gr.Column():
            output_image = gr.Image(label="Detected Image")
        with gr.Column():
            output_text = gr.Textbox(label="Object Count Results")
    
    detect_button = gr.Button("Detect")
    
    detect_button.click(
        fn=detect_objects,
        inputs=input_image,
        outputs=[output_image, output_text]
    )

# Launch the Gradio interface
iface.launch()