This repository contains implementations for various computer vision and deep learning projects. Each project demonstrates different techniques and algorithms used in the field of computer vision and deep learning.
| Project Name | Description |
|---|---|
| Image Classifier for Street View House Numbers (SVHN) Dataset | A deep learning model for classifying house numbers from the SVHN dataset, showcasing techniques for image classification. |
| Simple CNN Image Classifier for CIFAR-10 Dataset | A basic Convolutional Neural Network (CNN) implementation to classify images from the CIFAR-10 dataset. |
| Convolutional Neural Network Visualizer | A tool to visualize and understand the inner workings of Convolutional Neural Networks (CNNs). |
| Transfer Learning with ResNet-50 Architecture | An example of using transfer learning with the ResNet-50 model to classify images, showing the power of pre-trained models. |
| Neural Style Transfer Using TensorFlow | Implementation of neural style transfer to blend content and style images using TensorFlow. |
| Video Activity Recognition with Pretrained 3D ResNet | A project that uses a pretrained 3D ResNet model to recognize various activities in video sequences. |
| Faster Real-Time Video Processing Using Multi-Threading in Python | Optimizing video processing speed with multi-threading techniques in Python for real-time applications. |
| Real-Time Face Detection Using OpenCV | A real-time face detection application implemented using OpenCV, demonstrating object detection techniques. |
For running these projects, the following dependencies may be required (depending on the project):
- Python 3.x
- TensorFlow / Keras
- OpenCV
- NumPy
- Matplotlib
- Scikit-learn
- Other dependencies as specified in each project folder
-
Clone the repository:
git clone https://github.com/SoheilFM/computer-vision-deep-learning-projects.git
-
Navigate to the desired project directory:
cd project-folder-name -
Follow the instructions in the respective README of each project to set up the environment and run the code.
If you have suggestions or improvements, feel free to fork this repository, create a pull request, or open an issue.