⚠️ This repository is archived and no longer actively maintained.

A comprehensive collection of Jupyter and Zeppelin notebooks demonstrating various deep learning frameworks, techniques, and AWS SageMaker integrations. These notebooks were originally used in articles published on Medium.

This repository contains practical examples and tutorials covering:

• Deep Learning Frameworks: TensorFlow/Keras, PyTorch, MXNet, GluonCV
• AutoML: AutoGluon
• Graph Neural Networks: DGL (Deep Graph Library)
• NLP: ELMO, word embeddings, sentiment analysis
• Computer Vision: Classification, detection, segmentation
• AWS SageMaker: Training, inference, custom containers
• Traditional ML: Scikit-learn, Spark ML

dlnotebooks/
├── autogluon/          # AutoGluon examples
├── dgl/               # Deep Graph Library tutorials
├── gluoncv/           # Computer vision with GluonCV
├── keras/             # Keras/TensorFlow tutorials
├── ktrain/            # Ktrain NLP examples
├── mxnet/             # MXNet and Gluon tutorials
├── nlp/               # Natural Language Processing
├── pytorch/           # PyTorch tutorials
├── sagemaker/         # AWS SageMaker examples
├── scikit/            # Scikit-learn tutorials
└── spark/             # Apache Spark ML examples

• Python 3.6+
• Jupyter Notebook or JupyterLab
• Required packages (see individual folder READMEs for specific dependencies)

1. Clone this repository:

git clone https://github.com/julsimon/dlnotebooks.git
cd dlnotebooks

2. Install Jupyter:

pip install jupyter

3. Navigate to the specific framework folder and follow the instructions in its README.

• AutoGluon: Automated machine learning on Boston Housing dataset

• DGL: Karate Club community detection example

• GluonCV: Classification, detection, and segmentation models
• Keras: MNIST, Fashion MNIST, custom CNN implementations
• MXNet: Image classification, GANs, pre-trained models

• ELMO: Contextual word embeddings
• Word Embeddings: Similarity and analogy examples
• Ktrain: BERT-based sentiment analysis

• Image Classification: Transfer learning, custom algorithms
• Factorization Machines: MovieLens recommendation system
• DeepAR: Time series forecasting
• XGBoost: Gradient boosting examples

• Scikit-learn: Linear/logistic regression, decision trees, clustering, PCA
• Spark ML: Spam classification, clustering with SageMaker integration

Each subfolder contains:

• Jupyter notebooks with detailed explanations
• Supporting data files (where applicable)
• Docker configurations (for SageMaker examples)
• README files with specific setup instructions

Note: This repository is archived and no longer accepting contributions. The code is provided as-is for educational and reference purposes.

This project is licensed under the MIT License - see the LICENSE file for details.

• Original Medium Articles
• Jupyter Documentation
• AWS SageMaker Documentation

Disclaimer: This repository is archived and may contain outdated code or dependencies. Use at your own risk and consider updating frameworks and libraries for production use.