Skip to content

A structured deep learning learning journey using PyTorch including neural networks, CNNs, and experiments.

Notifications You must be signed in to change notification settings

KavinKohli/Deep-Learning-PyTorch

Repository files navigation

Deep-Learning-PyTorch

A complete learning repository for Deep Learning using PyTorch, covering everything from tensors and neural networks to training pipelines and real-world projects.

This repository is built as a learning + portfolio project — every notebook here represents a concept I have learned and implemented from scratch.


Why this repository exists

Deep Learning is not about just using libraries — it is about understanding:

  • How neural networks work
  • How gradients flow
  • How loss functions & optimizers train models
  • How real training pipelines are built

This repository documents that journey in a structured, practical way.


Tech Stack

  • Python
  • PyTorch
  • Jupyter Notebook
  • NumPy
  • Matplotlib

Topics Covered

(Updated as I learn more)

📅 Deep Learning with PyTorch — Daily Progress

Day 1 — PyTorch Basics

Learned what PyTorch is, why it’s used, how to import it, and the core idea of tensors.

Day 2 — Tensor Creation

Created tensors (scalars, vectors, matrices), used zeros, ones, random tensors, and explored shapes.

Day 3 — Tensor Operations

Performed tensor arithmetic, matrix multiplication, aggregations, and inspected tensor properties.

Day 4 — Tensor Manipulation + NumPy

Learned reshaping, stacking, indexing, and converting between NumPy arrays and PyTorch tensors.

Day 5 — Device & Reproducibility

Set random seeds, ensured reproducibility, and moved tensors between CPU and GPU.

Day 6 — Binary Classification

Built a binary classification model, prepared data, and defined loss functions and optimizers.

Day 7 — Training Loop & Evaluation

Implemented training loops, backpropagation, evaluation metrics, and visualized predictions.

Day 8 — Multiclass Classification

Trained a multiclass classifier using Softmax and CrossEntropyLoss and evaluated performance.

Day 9 — Putting It All Together

Improved models using non-linearities and summarized the full classification pipeline.

Day 10 — Computer Vision Introduction

Understood what computer vision is, how images are represented as tensors, and how PyTorch handles image data.

Day 11 — Baseline Computer Vision Model

Built a baseline image classification model and learned the full training + evaluation flow on image data.

Day 12 — Improving the Vision Model

Improved the baseline model by adjusting architecture, epochs, and training strategy.

Day 13 — Convolutional Neural Networks (CNNs)

Learned how CNNs work, implemented convolutional layers, and understood feature extraction.

Day 14 — CNN Training & Evaluation

Trained a CNN model, evaluated performance, and visualized predictions on image data.

Day 15 — Computer Vision Summary

Reviewed the full computer vision pipeline and summarized learnings from Chapter 3.


(This structure grows as new topics and projects are added.)


How to Run

1: Clone the repository

git clone https://github.com/KavinKohli/Deep-Learning-PyTorch.git
cd Deep-Learning-PyTorch

About

A structured deep learning learning journey using PyTorch including neural networks, CNNs, and experiments.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published