Welcome to my Deep Learning Assignments repository! This repository contains four assignments that cover various aspects of deep learning, implemented using PyTorch. Each assignment focuses on specific topics, providing hands-on experience and learning opportunities.
Learn the basics of loading data, creating a train/test split, and building a simple linear regression model using PyTorch. Train the model with the gradient descent algorithm to solve regression problems.
Dive into neural networks, deep neural networks, loss functions, and optimization techniques. Build a simple neural network using numpy to understand backpropagation. Explore gradient checking, stochastic gradient descent (SGD), regularization, and hyperparameter tuning.
Explore the world of convolutional neural networks (CNNs) in PyTorch. Write a custom dataset in PyTorch with training, validation, and test sets. Build and train a CNN to classify images, gaining practical experience with image recognition tasks.
Delve into the realm of generative adversarial networks (GANs) in PyTorch. Build a GAN, load pretrained parameters, and train the network for image generation. Evaluate the performance of your GAN and understand the principles behind generative models.
- Assignment1: Simple Linear Regression
- Assignment2: Neural Network Fundamentals
- Assignment3: Convolutional Neural Network (CNN)
- Assignment4: Generative Adversarial Network (GAN)
Each assignment folder contains its own set of instructions, code, and datasets. Follow the README.md file in each assignment folder for detailed information on setup and execution.
- Python
- PyTorch
- NumPy
- Other dependencies specific to each assignment (check respective README files)
These assignments are designed to provide a practical understanding of fundamental deep learning concepts. Feel free to explore, modify, and enhance the code to deepen your knowledge in the fascinating field of deep learning. Do not copy it for other purpose.
Happy learning! 🚀