Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- <!DOCTYPE html>
- <html lang="en">
- <head>
- <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.4.0/css/bootstrap.min.css">
- <style type="text/css">
- .previous {
- background-color: #f1f1f1;
- color: black;
- }
- .round {
- border-radius: 50%;
- }
- a {
- text-decoration: none;
- display: inline-block;
- padding: 8px 16px;
- }
- a:hover {
- background-color: #ddd;
- color: black;
- }
- </style>
- </head>
- <body>
- <nav class="navbar navbar-inverse">
- <div class="container-fluid">
- <div class="navbar-header">
- <a href="home.html" class="previous round">‹</a>
- <!-- <a class="navbar-brand" href="#">Deep Learning Course Projects</a> -->
- </div>
- </div>
- </nav>
- <div class="text-center">
- <h2>Car Brand detection</h2>
- <h5>Ahmed Adel</h5>
- <h5>Fady George</h5>
- </div>
- <h2>Problem Statment</h2>
- <h3> There are many people who are crazy about cars so
- we decided to implement this idea which is detecting
- car make-year-model from an image.</h3>
- <h2>Input/ output Example</h2>
- <h2>Gantt chart</h2>
- <h2>Dataset</h2>
- <h3> We used Stanford Car Dataset by classes folder which has 16185 images </h3>
- <h2>State of the art</h2>
- <h3>The best accuracy was 88% implemented by samuel
- Freshman where the network trained on 49 classes
- while the accuracy of GoogleNet was 80% by having
- 196 classes.</h3>
- <h2>Data pre-processing</h2>
- <h3>We have applied data augmentation as follows : random horizontal flips , random rotation < 30 degree , random zoom < 10 and random lighting < 10</h3>
- <h2>Models Used</h2>
- <h3>1) Yolo v3 for image segmentation</h3>
- <h3>2) ResNet34 for image detection</h3>
- <h3>3) VGG16 for image detection</h3>
- <h2>Fine Tuning apllied</h2>
- <h2>Results</h2>
- <h3>VGG16 reached validation accuracy 71%</h3>
- <h3>Fine tuning ResNet34 the model was able to reach 87% of
- accuracy</h3>
- </body>
- </html>
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement