https://github.com/datarohit/learning-pytorch

Explore my journey of learning PyTorch through a series of hands-on projects! This GitHub repository showcases my progress in mastering PyTorch fundamentals, including linear regression, multi-class classification, non-linear activation functions, CNN for Fashion MNIST, transfer learning, and model deployment.
https://github.com/datarohit/learning-pytorch

deep-learning hands hands-on machine-learning pytorch

Last synced: about 1 month ago
JSON representation

Explore my journey of learning PyTorch through a series of hands-on projects! This GitHub repository showcases my progress in mastering PyTorch fundamentals, including linear regression, multi-class classification, non-linear activation functions, CNN for Fashion MNIST, transfer learning, and model deployment.

• Host: GitHub
• URL: https://github.com/datarohit/learning-pytorch
• Owner: DataRohit
• Created: 2023-07-26T02:06:55.000Z (almost 3 years ago)
• Default Branch: master
• Last Pushed: 2023-07-26T02:23:19.000Z (almost 3 years ago)
• Last Synced: 2025-02-15T07:47:27.325Z (over 1 year ago)
• Topics: deep-learning, hands, hands-on, machine-learning, pytorch
• Language: Jupyter Notebook
• Homepage:
• Size: 5.63 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# PyTorch Notebooks

This repository contains a collection of Jupyter notebooks that I created while learning PyTorch. I used the following resource to learn PyTorch:

- [Learn PyTorch](https://www.learnpytorch.io/)

The notebooks cover various topics and tasks related to PyTorch, including linear regression, multi-class classification, CNN, transfer learning, and more.

## Notebooks

1. `00_pytorch_fundamentals.ipynb` - An introduction to PyTorch fundamentals.

2. `01_pytorch_workflow_linear_regression_v1.ipynb` - Linear regression using PyTorch (Version 1).

3. `01_pytorch_workflow_linear_regression_v2.ipynb` - Linear regression using PyTorch (Version 2).

4. `02_pytorch_multi_class_classification.ipynb` - Multi-class classification with PyTorch.

5. `02_pytorch_multi_layer_binary_classification.ipynb` - Binary classification with multiple layers in PyTorch.

6. `02_pytorch_multi_layer_non_linear_classification.ipynb` - Non-linear classification with multiple layers in PyTorch.

7. `02_pytorch_multi_layer_regression.ipynb` - Multi-layer regression using PyTorch.

8. `02_pytorch_non_linear_activation_functions.ipynb` - Exploring non-linear activation functions in PyTorch.

9. `02_pytorch_non_linear_spiral_classification.ipynb` - Non-linear spiral classification with PyTorch.

10. `02_pytorch_simple_binary_classification.ipynb` - Simple binary classification using PyTorch.

11. `03_pytorch_fashion_mnist_cnn.ipynb` - Fashion MNIST classification using CNN in PyTorch.

12. `03_pytorch_fashion_mnist_linear.ipynb` - Fashion MNIST classification using linear models in PyTorch.

13. `03_pytorch_fashion_mnist_non_linear.ipynb` - Fashion MNIST classification using non-linear models in PyTorch.

14. `03_pytorch_fashion_mnist_resnet50.ipynb` - Fashion MNIST classification using ResNet50 in PyTorch.

15. `04_pytorch_custom_dataset.ipynb` - Working with custom datasets in PyTorch.

16. `05_pytorch_transfer_learning.ipynb` - Transfer learning with PyTorch.

17. `06_pytorch_experiment_tracking.ipynb` - Experiment tracking with PyTorch.

18. `07_pytorch_vision_transformer.ipynb` - Vision Transformer (ViT) implementation in PyTorch.

19. `08_pytorch_model_deployment.ipynb` - Model deployment using PyTorch.

20. `09_pytorch_quick_pytorch_2.ipynb` - Quick introduction to PyTorch 2.0.

## Learning Resource

I used the following resource to learn PyTorch:

- [Learn PyTorch](https://www.learnpytorch.io/)

## Acknowledgments

Special thanks to **Daniel Bourke** (Github username: mrdbourke) for providing valuable learning material and code examples. You can find his repository on PyTorch Deep Learning here: [PyTorch Deep Learning](https://github.com/mrdbourke/pytorch-deep-learning).

Feel free to explore the notebooks and utilize the resources mentioned above to enhance your PyTorch skills. Happy learning!

**Note**: If you plan to use any part of this repository or the models, please adhere to the respective licenses and terms of use.