https://github.com/ricardorobledo/dl_for_computer_vision
Personal journey and practical implementations inspired by Computer Vision with Deep Learning materials from Machine Learning Mastery. Focused on image preprocessing, CNNs, transfer learning, classification, object detection, and face recognition to apply computer vision techniques to real-world problems.
https://github.com/ricardorobledo/dl_for_computer_vision
classification face-recognition object-detection python3 tensorflow yolo
Last synced: 2 months ago
JSON representation
Personal journey and practical implementations inspired by Computer Vision with Deep Learning materials from Machine Learning Mastery. Focused on image preprocessing, CNNs, transfer learning, classification, object detection, and face recognition to apply computer vision techniques to real-world problems.
- Host: GitHub
- URL: https://github.com/ricardorobledo/dl_for_computer_vision
- Owner: RicardoRobledo
- Created: 2025-07-17T23:58:09.000Z (12 months ago)
- Default Branch: main
- Last Pushed: 2025-07-18T00:00:01.000Z (12 months ago)
- Last Synced: 2025-10-26T20:56:12.381Z (8 months ago)
- Topics: classification, face-recognition, object-detection, python3, tensorflow, yolo
- Language: Jupyter Notebook
- Homepage:
- Size: 4.29 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Computer Vision Notebook
This notebook is based on the comprehensive materials from [machinelearningmastery.com](https://machinelearningmastery.com/) and covers fundamental and advanced topics in computer vision, with a strong focus on practical deep learning applications.
## Key Topics Covered
- **Foundations of Computer Vision:** introduction, challenges, and main tasks.
- **Deep Learning for Computer Vision:** types of networks, common problems, and the promises of deep learning.
- **Image Loading and Manipulation:** using PIL/Pillow, Keras, and techniques for scaling and normalizing image data.
- **Data Augmentation and Preparation:** data augmentation methods, handling large datasets, and preprocessing techniques.
- **Convolutions and Pooling Layers:** basics, architecture, and workings of convolutional neural networks (CNNs).
- **Milestone CNN Architectures:** LeNet-5, AlexNet, VGG, Inception, ResNet, and other architectural innovations.
- **Using Pre-Trained Models and Transfer Learning:** how to apply and adapt pre-trained models.
- **Image Classification:** from fashion images (Fashion-MNIST), small object photos (CIFAR-10), to dogs vs. cats classification.
- **Object Detection:** R-CNN family, YOLO, Mask R-CNN, and how to develop new object detection models.
- **Face Recognition:** classical and deep learning methods including VGGFace and FaceNet.
This notebook provides detailed explanations, step-by-step examples, and practical projects for those who want to apply computer vision with deep learning to real-world problems.