Computer Vision With PyTorch

This repository contains Jupyter notebooks demonstrating fundamental concepts in neural networks and computer vision using PyTorch.

Notebooks

Auto_Gradient_Of_Tensor.ipynb: Demonstrates automatic gradient computation for tensors in PyTorch.
Backpropagation.ipynb: Explains the backpropagation algorithm for computing gradients in neural networks.
Building_a_neural_network_using_PyTorch_on_a_toy_dataset.ipynb: Builds a neural network using PyTorch on a simple toy dataset.
Chain_Rule.ipynb: Demonstrates the chain rule in calculus, essential for backpropagation.
Feed_Forward_Propagation.ipynb: Implements feed-forward propagation in a neural network, showing how inputs are processed through layers to produce outputs.
Gradient_Descent.ipynb: Demonstrates gradient descent optimization algorithm used for training neural networks, including weight updates and loss minimization.
Implementing_custom_loss_function.ipynb: Shows how to implement a custom loss function in PyTorch.
Initialinzing_A_Tensor.ipynb: Covers different ways to initialize tensors in PyTorch.
Learning_Rate.ipynb: Explores the impact of different learning rates on the training process of neural networks.
Oeprations_On_Tensors.ipynb: Demonstrates various operations that can be performed on tensors in PyTorch.
Specifying_batch_size_while_training_a_model.ipynb: Explains how to specify batch size when training a model in PyTorch.

Open the notebooks in Jupyter Lab or VS Code to run the code cells and see the visualizations.

Modern Computer Vision with PyTorch - Official repository for the book "Modern Computer Vision with PyTorch" by Packt Publishing.

This project is for educational purposes.