Skip to content

The Deep Learning Notes repository is a comprehensive resource for deep learning enthusiasts, with detailed notebooks, modular implementations and in-depth analysis.

License

Notifications You must be signed in to change notification settings

semilleroCV/deep-learning-notes

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

76 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

deep-learning-notes

Deep Learning Notes

Welcome to the Deep Learning Notes repository! This repository serves as a comprehensive resource for deep learning enthusiasts, providing detailed notebooks, modular implementations, and in-depth analyses related to various aspects of deep learning. Below is the structure and a brief description of each directory within the repository:

Project Organization

├── assets             <- Static files like images and badges.
│
├── automation
│   │
│   └── autogenerate_notebooks_table.py Script that performs the update of the main readme based on
│        notebooks-table-data.csv
│
├── core <- Common utility functions used across notebooks.
│    │
│    ├── __init__.py   <- Makes core a Python module
│    │
│    └── utils.py      <- Useful functions
│
├── notebooks          <- Jupyter notebooks. Naming convention is a short `-` delimited description,
│   │                    e.g. `cross-entropy-loss`.
│   │
│   ├── architectures  <- Implementations of architectures, e.g. UNET.
│   │
│   ├── losses         <- Examples of loss functions, e.g. NLLLoss.
│   │
│   ├── metrics        <- Demonstrations of metrics, e.g. IoU
│   │
│   ├── modules        <- Implementations of a module, e.g. Xception module.
│   │
│   └── data_exploration    <- Exploration of a dataset, e.g. MNIST.
│
├── papers             <- Markdown articles about important deep learning papers.
│
├── CONTRIBUTING.md    <- How to contribute to the project.
│
├── LICENSE            <- Open-source license (MIT)
│
└── README.md          <- Overview of the repository.

🏗️ Architectures (9 notebooks)

notebook open in colab repository / paper
Network In Network Colab arXiv
Xception Colab arXiv
U-Net Colab arXiv
DenseNet Colab arXiv
Mobilenet V1 Colab arXiv
Inception V1 Colab arXiv
MLP Mixer Colab arXiv
Vision Transformer (ViT) Colab arXiv
ResNet Colab arXiv

❌ Loss Functions (2 notebooks)

notebook open in colab repository / paper
Focal Loss Colab GitHub arXiv
CELoss vs NLLLoss Colab

📏 Metrics (1 notebooks)

notebook open in colab repository / paper
Intersection Over Union (IoU) Colab arXiv

🧩 Modules (2 notebooks)

notebook open in colab repository / paper
Pixel Shuffle Colab arXiv
Multi-Head Attention Colab arXiv

🔍 Data Exploration (1 notebooks)

notebook open in colab repository / paper
GloVe Word Embeddings Colab GitHub NLP Stanford

🐞 Bugs & 🦸 Contribution

Computer Vision progresses rapidly! Occasionally, our notebooks may lag a little behind the constantly advancing libraries. If you encounter any issues with the functionality of our notebooks, please create a bug report to inform us.

If you'd like to add a new notebook or improve an existing one, please take a peek at our contribution guide. There you can find all the information you need.

We are here for you, so don't hesitate to reach out.

💻 Run Locally

We try to make it as easy as possible to run our Notebooks in Colab. However, if you prefer to run them locally follow the instructions below. We recommend not to install the dependencies globally, use virtual environments.

# Clone the repository and navigate to the root directory:
git clone [email protected]:semilleroCV/deep-learning-notes.git
cd deep-learning-notes

# Set up the Python virtual environment and activate it:
python3 -m venv venv
# For Unix-based systems (Linux/Mac)
source venv/bin/activate
# For Windows systems
# venv\Scripts\activate

# (Optional) Install and run jupyter notebook:
pip install notebook
jupyter notebook

About

The Deep Learning Notes repository is a comprehensive resource for deep learning enthusiasts, with detailed notebooks, modular implementations and in-depth analysis.

Topics

Resources

License

Stars

Watchers

Forks