Neural Network Tutorials - Herong's Tutorial Examples - v1.22, by Herong Yang
What Is PyTorch
This section provides a quick introduction on PyTorch, which is a Python-based scientific computing package targeted at two sets of audiences: A replacement for NumPy to use the power of GPUs and a deep learning research platform that provides maximum flexibility and speed.
What Is PyTorch? PyTorch is a Python-based scientific computing package targeted at two sets of audiences: A replacement for NumPy to use the power of GPUs and a deep learning research platform that provides maximum flexibility and speed. PyTorch was originally developed as a research framework by a Facebook intern in 2017.
PyTorch is divided into the following components:
1. torch - Numpy like library for tensors with GPU support.
2. torch.autograd - Give differentiation support for all operations on tensors.
3. torch.nn - Provides classes necessary for building neural networks.
4. torch.optim - Provides optimization methods for different neural network models.
5. torch.utils - Provides classes for data processing.
6. torch.nn.Module - A container that all models (layers with trainable parameters) should inherited from because it tracks the trainable parameters.
7. torch.nn.functional - A functional interface (no trainable parameters) that has ops for building neural networks (loss and activation functions).
Table of Contents
Deep Playground for Classical Neural Networks
Building Neural Networks with Python
Simple Example of Neural Networks
TensorFlow - Machine Learning Platform
►PyTorch - Machine Learning Platform
Commonly Used 'torch' functions
CNN (Convolutional Neural Network)
RNN (Recurrent Neural Network)
GAN (Generative Adversarial Network)