Upload 8 files

Browse files

Files changed (8) hide show

Objectdetection/__pycache__/model_loader.cpython-310.pyc +0 -0
Objectdetection/__pycache__/utils.cpython-310.pyc +0 -0
Objectdetection/model_loader.py +14 -0
Objectdetection/objectdetection.py +35 -0
Objectdetection/objectdetection_model.pth +3 -0
Objectdetection/static/style.css +45 -0
Objectdetection/templates/index.html +48 -0
Objectdetection/utils.py +54 -0

Objectdetection/__pycache__/model_loader.cpython-310.pyc ADDED Viewed

Binary file (671 Bytes). View file

Objectdetection/__pycache__/utils.cpython-310.pyc ADDED Viewed

Binary file (1.55 kB). View file

Objectdetection/model_loader.py ADDED Viewed

	@@ -0,0 +1,14 @@

+import torch
+import torchvision
+from torchvision.models.detection.faster_rcnn import FastRCNNPredictor
+def get_model(num_classes):
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)
+    in_features = model.roi_heads.box_predictor.cls_score.in_features
+    model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)
+    model.to(device)
+    model.eval()
+    return model, device

Objectdetection/objectdetection.py ADDED Viewed

	@@ -0,0 +1,35 @@

+from flask import Flask, render_template, request, send_from_directory
+import os
+from model_loader import get_model
+from utils import process_video
+app = Flask(__name__)
+UPLOAD_FOLDER = 'static/uploads'
+RESULT_FOLDER = 'static/results'
+os.makedirs(UPLOAD_FOLDER, exist_ok=True)
+os.makedirs(RESULT_FOLDER, exist_ok=True)
+num_classes = 21
+model, device = get_model(num_classes)
+@app.route('/', methods=['GET', 'POST'])
+def index():
+    if request.method == 'POST':
+        file = request.files['video']
+        if file:
+            filepath = os.path.join(UPLOAD_FOLDER, file.filename)
+            file.save(filepath)
+            output_path = os.path.join(RESULT_FOLDER, 'result_' + file.filename)
+            result_path = process_video(filepath, model, output_path, device)
+            return render_template('index.html', video_result=result_path)
+    return render_template('index.html', video_result=None)
+@app.route('/static/<path:path>')
+def send_static(path):
+    return send_from_directory('static', path)
+if __name__ == '__main__':
+    app.run(debug=True)

Objectdetection/objectdetection_model.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f516fd07beeb67a4a5939b8778f0b17c9fd6a70965ccc30ea9d84c845e5182e7
+size 166116798

Objectdetection/static/style.css ADDED Viewed

	@@ -0,0 +1,45 @@

+body {
+    font-family: Arial, sans-serif;
+    background-color: #f8f9fa;
+    padding: 40px;
+    text-align: center;
+}
+h1, h2 {
+    color: #333;
+}
+form {
+    background-color: #fff;
+    padding: 20px;
+    margin: 0 auto 30px;
+    border-radius: 8px;
+    box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1);
+    display: inline-block;
+}
+input[type="file"],
+select,
+input[type="submit"] {
+    margin: 10px;
+    padding: 10px;
+    font-size: 16px;
+}
+input[type="submit"] {
+    background-color: #007bff;
+    color: white;
+    border: none;
+    cursor: pointer;
+    border-radius: 5px;
+}
+input[type="submit"]:hover {
+    background-color: #0056b3;
+}
+img, video {
+    margin-top: 15px;
+    border-radius: 10px;
+    border: 2px solid #ccc;
+}

Objectdetection/templates/index.html ADDED Viewed

	@@ -0,0 +1,48 @@

+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>Object Detection</title>
+    <style>
+        body {
+            font-family: Arial, sans-serif;
+            background: #f5f5f5;
+            padding: 30px;
+            text-align: center;
+        }
+        .container {
+            background: white;
+            padding: 20px;
+            border-radius: 8px;
+            box-shadow: 0 2px 8px rgba(0,0,0,0.1);
+            display: inline-block;
+        }
+        input[type="file"], input[type="submit"] {
+            margin: 10px;
+            padding: 8px 12px;
+            border-radius: 4px;
+        }
+        video {
+            max-width: 100%;
+            margin-top: 20px;
+        }
+    </style>
+</head>
+<body>
+    <div class="container">
+        <h1>Object Detection (Video)</h1>
+        <form method="POST" enctype="multipart/form-data">
+            <input type="file" name="video" accept="video/*" required>
+            <br>
+            <input type="submit" value="Upload & Detect">
+        </form>
+        {% if video_result %}
+            <h2>Result Video</h2>
+            <video controls>
+                <source src="{{ video_result }}" type="video/mp4">
+                Your browser does not support the video tag.
+            </video>
+        {% endif %}
+    </div>
+</body>
+</html>

Objectdetection/utils.py ADDED Viewed

	@@ -0,0 +1,54 @@

+import cv2
+import torch
+import os
+import numpy as np
+from torchvision import transforms
+def process_video(video_path, model, output_path, device):
+    transform = transforms.Compose([
+        transforms.ToTensor()
+    ])
+    cap = cv2.VideoCapture(str(video_path))
+    if not cap.isOpened():
+        raise IOError(f"Cannot open video: {video_path}")
+    fourcc = cv2.VideoWriter_fourcc(*'XVID')
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+    frame_skip = 2
+    frame_count = 0
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
+        resized_frame = cv2.resize(frame, (640, 480))
+        if frame_count % frame_skip == 0:
+            rgb_frame = cv2.cvtColor(resized_frame, cv2.COLOR_BGR2RGB)
+            img_tensor = transform(rgb_frame).to(device)
+            with torch.no_grad():
+                prediction = model([img_tensor])[0]
+            for box, score, label in zip(prediction["boxes"], prediction["scores"], prediction["labels"]):
+                if score > 0.5:
+                    x1, y1, x2, y2 = map(int, box)
+                    cv2.rectangle(resized_frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+                    cv2.putText(resized_frame, f"{label.item()}:{score:.2f}", (x1, y1 - 10),
+                                cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 0), 2)
+        output_frame = cv2.resize(resized_frame, (width, height))
+        out.write(output_frame)
+        frame_count += 1
+    cap.release()
+    out.release()
+    return output_path