app.py

import torch
import numpy as np
import gradio as gr
import cv2
import time
import os
from pathlib import Path

# Create cache directory for models
os.makedirs("models", exist_ok=True)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"Using device: {device}")

# Load YOLOv5 Model
model_path = Path("models/yolov5n.pt")
if model_path.exists():
    print(f"Loading model from cache: {model_path}")
    model = torch.hub.load("ultralytics/yolov5", "custom", path=str(model_path), source="local").to(device)
else:
    print("Downloading YOLOv5n model and caching...")
    model = torch.hub.load("ultralytics/yolov5", "yolov5n", pretrained=True).to(device)
    torch.save(model.state_dict(), model_path)

# Configure model
model.conf = 0.5
model.iou = 0.5
model.classes = None
if device.type == "cuda":
    model.half()
else:
    torch.set_num_threads(os.cpu_count())
model.eval()

# Generate colors for bounding boxes
np.random.seed(42)
colors = np.random.uniform(0, 255, size=(len(model.names), 3))

def detect_objects(image):
    if image is None:
        return None
    
    output_image = image.copy()
    results = model(image, size=640)
    detections = results.pred[0].cpu().numpy()
    
    for *xyxy, conf, cls in detections:
        x1, y1, x2, y2 = map(int, xyxy)
        class_id = int(cls)
        color = colors[class_id].tolist()
        cv2.rectangle(output_image, (x1, y1), (x2, y2), color, 3, lineType=cv2.LINE_AA)
        label = f"{model.names[class_id]} {conf:.2f}"
        cv2.putText(output_image, label, (x1, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (255, 255, 255), 2)
    
    return output_image

def process_video(video_path):
    cap = cv2.VideoCapture(video_path)
    if not cap.isOpened():
        return "Error: Could not open video file."
    
    frame_width = int(cap.get(3))
    frame_height = int(cap.get(4))
    fps = cap.get(cv2.CAP_PROP_FPS)
    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
    output_path = "output_video.mp4"
    out = cv2.VideoWriter(output_path, fourcc, fps, (frame_width, frame_height))
    
    while cap.isOpened():
        ret, frame = cap.read()
        if not ret:
            break
        
        img = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
        results = model(img, size=640)
        detections = results.pred[0].cpu().numpy()

        for *xyxy, conf, cls in detections:
            x1, y1, x2, y2 = map(int, xyxy)
            class_id = int(cls)
            color = colors[class_id].tolist()
            cv2.rectangle(frame, (x1, y1), (x2, y2), color, 3, lineType=cv2.LINE_AA)
            label = f"{model.names[class_id]} {conf:.2f}"
            cv2.putText(frame, label, (x1, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (255, 255, 255), 2)
        
        out.write(frame)
    
    cap.release()
    out.release()
    return output_path

# Gradio Interface
with gr.Blocks(title="YOLOv5 Object Detection") as demo:
    gr.Markdown("# YOLOv5 Object Detection (Image & Video)")
    
    with gr.Tab("Image Detection"):
        img_input = gr.Image(label="Upload Image", type="numpy")
        img_output = gr.Image(label="Detected Objects", type="numpy")
        img_submit = gr.Button("Detect Objects")
        img_submit.click(fn=detect_objects, inputs=img_input, outputs=img_output)
    
    with gr.Tab("Video Detection"):
        vid_input = gr.Video(label="Upload Video")
        vid_output = gr.Video(label="Processed Video")
        vid_submit = gr.Button("Process Video")
        vid_submit.click(fn=process_video, inputs=vid_input, outputs=vid_output)
    
    demo.launch()