Neural Network Tutorials - Herong's Tutorial Examples - v1.22, by Herong Yang
Commonly Used 'torch' functions
This section describes some commonly used PyTorch functions, including add(), multiply(), matmul(), tf.reduce_sum(), tf.nn.softmax(), etc.
As a quick reference, here is a list of commonly used PyTorch, "torch" library, functions:
1. Functions provided by the "torch" module itself:
import torch
torch.empty(m, n, ...) - Creates an empty tensor with the given shape.
torch.rand(m, n, ...) - Creates a tensor of random values with the given shape.
torch.torch.zeros(m, n, ...) - Creates a tensor of zeros with the given shape.
torch.tensor([[...],[...],...]) - Creates an tensor with the given date.
torch.rand_like(a) - Creates an empty tensor with the given shape.
a.size() - Returns the size (shape) of this tensor.
torch.add(a,b) - Creates a tensor by taking the sum of two given tensors. Same as (a+b).
a.add_(b) - Updates this tensor by adding values from the given tensor.
x.view(n, m, ...) - Creates a tensor by reshaping this tensor with the given shape.
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)