1. Secure and Private AI

course source : https://classroom.udacity.com/courses/ud185

other course : https://www.udacity.com/school-of-ai

1.1. Deep learning with PyTorch

• https://research.fb.com/category/facebook-ai-research/
• Notebooks : https://github.com/udacity/deep-learning-v2-pytorch

1.1.1. Install Python3

• create a python3.7.X environment : conda create -n py37 python=3.7 anaconda
• activate the environment conda activiate py37
• deactivate the environment conda deactivate
• determining my environment : conda info –envs

1.1.2. Install PyTorch

• Install Conda : https://conda.io/en/latest/

  • install Anaconda : https://docs.anaconda.com/anaconda/install/
  • or install Miniconda : https://docs.conda.io/en/latest/miniconda.html

  • Some commands

    • managing environments : https://conda.io/projects/conda/en/latest/user-guide/getting-started.html#managing-environments
    • example of commands : conda search scipy, conda install scipy, conda build my_fun_package, conda update conda

• Install PyTorch https://pytorch.org/get-started/locally/

  • conda install pytorch torchvision cudatoolkit=10.0 -c pytorch

• Install numpy, jupyter and notebook :

  • conda install numpy jupyter notebook

1.1.3. Launching Jupyter Notebook App

• jupyter notebook - https://jupyter-notebook-beginner-guide.readthedocs.io/en/latest/execute.html

1.1.4. Udacity course : Deep Learning with PyTorch

This repo contains notebooks and related code for Udacity’s Deep Learning with PyTorch lesson. This lesson appears in our [AI Programming with Python Nanodegree program](https://www.udacity.com/course/ai-programming-python-nanodegree–nd089).

• Part 1: Introduction to PyTorch and using tensors
• Part 2: Building fully-connected neural networks with PyTorch
• Part 3: How to train a fully-connected network with backpropagation on MNIST
• Part 4: Exercise - train a neural network on Fashion-MNIST
• Part 5: Using a trained network for making predictions and validating networks
• Part 6: How to save and load trained models
• Part 7: Load image data with torchvision, also data augmentation
• Part 8: Use transfer learning to train a state-of-the-art image classifier for dogs and cats

1.2. Tools

• Gym is a toolkit for developing and comparing reinforcement learning algorithms. It supports teaching agents everything from walking to playing games like Pong or Pinball. https://gym.openai.com/
• ONNX is an open format to represent deep learning models. With ONNX, AI developers can more easily move models between state-of-the-art tools and choose the combination that is best for them. ONNX is developed and supported by a community of partners. https://onnx.ai/