Table of Contents

Tutorials by Technology

TensorFlow is a free and open-source software library for machine learning and artificial intelligence. It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks.

PyTorch is an open source machine learning framework based on the Torch library, used for applications such as computer vision and natural language processing, primarily developed by Meta AI. It is free and open-source software released under the Modified BSD license.

NumPy is a library for the Python programming language, adding support for large, multi-dimensional arrays and matrices, along with a large collection of high-level mathematical functions to operate on these arrays.

Python is a high-level, interpreted, general-purpose programming language. Its design philosophy emphasizes code readability with the use of significant indentation. Python is dynamically-typed and garbage-collected.

Apache MXNet is an open-source deep learning software framework, used to train and deploy deep neural networks. It is scalable, allowing for fast model training and supports a flexible programming model and multiple programming languages.

A quick, chronological list of every single published video

PyTorch Tensor To Float: Convert a PyTorch Tensor To A Floating Number Data Type

Build an autograd backward graph by performing operations on PyTorch Autograd Tensors

AvgPool2D - Use the PyTorch AvgPool2D Module to incorporate average pooling into a PyTorch neural network

PyTorch Autograd - Use PyTorch's requires_grad to define a PyTorch Tensor with Autograd

BatchNorm2d - Use the PyTorch BatchNorm2d Module to accelerate Deep Network training by reducing internal covariate shift

PyTorch Tensor To List: Use PyTorch tolist() to convert a PyTorch Tensor into a Python list

Use the PyTorch view method to manage Tensor Shape within a Convolutional Neural Network

tf.contrib.distributions.percentile - Calculate TensorFlow Median Value using the percentile distribution and the interpolation methods

Construct A Custom PyTorch Model by creating your own custom PyTorch module by subclassing the PyTorch nn.Module class

Use PyTorch's nn.ReLU and add_module operations to define a ReLU layer

Use PyTorch nn.Sequential and PyTorch nn.Conv2d to define a convolutional layer in PyTorch

tf.transpose - Use TensorFlow's transpose operation to transpose a TensorFlow matrix tensor

Use PyTorch's nn.Sequential and add_module operations to define a sequential neural network container

tf.dtype - Use TensorFlow's dtype operation to print and check a TensorFlow's Tensor data type

PyTorch item - Use PyTorch's item operation to convert a 0-dim PyTorch Tensor to a Python number

PyTorch Min - Use PyTorch's min operation to calculate the min of a PyTorch tensor

PyTorch Max - Use PyTorch's max operation to calculate the max of a PyTorch tensor

Find out which version of PyTorch is installed in your system by printing the PyTorch version

PyTorch Matrix Multiplication - Use torch.mm to do a PyTorch Dot Product

tf.reduce_min - Use TensorFlow's reduce_min operation to get the minimum value of a TensorFlow Tensor

Use TensorFlow's random_uniform operation to create a TensorFlow Tensor with a random uniform distribution

Use PyTorch's To List (tolist) operation to convert a PyTorch Tensor to a Python list

Use the TensorFlow reshape operation to flatten a TensorFlow Tensor

Use the TensorFlow get_shape operation to print the static shape of a TensorFlow tensor as a list

Find out which version of TensorFlow is installed in your system by printing the TensorFlow version

Use the TensorFlow Get Operations Operation to list all Tensor names in a TensorFlow graph

PyTorch List to Tensor - Use the PyTorch Tensor operation (torch.tensor) to convert a Python list object into a PyTorch Tensor

Augment the CIFAR10 Dataset Using the TorchVision RandomHorizontalFlip (transforms.RandomHorizontalFlip) and RandomCrop (transforms.RandomCrop) Transforms

Use Torchvision CenterCrop Transform (torchvision.transforms.CenterCrop) to do a rectangular crop of a PIL image

Use Torchvision CenterCrop Transform (torchvision.transforms.CenterCrop) to do a square crop of a PIL image

Convert a python list into a TensorFlow Tensor using the TensorFlow convert_to_tensor functionality

Get the shape of a PyTorch Tensor as a list of integers by using the PyTorch Shape operation and the Python List constructor

PyTorch Stack - Use the PyTorch Stack operation (torch.stack) to turn a list of PyTorch Tensors into one tensor

Check the TorchVision version by printing the version parameter

Use TensorFlow Name Scopes (tf.name_scope) to group graph nodes in the TensorBoard web service so that your graph visualization is legible

Use TensorFlow Summary File Writer (tf.summary.FileWriter) and the TensorBoard command line utility to visualize a TensorFlow Graph in the TensorBoard web service

Use the Torchvision Transforms Parameter in the initialization function to apply transforms to PyTorch Torchvision Datasets during the data import process

Use the TensorBoard command line utility to launch the TensorFlow TensorBoard web service

Use Torchvision Transforms Normalize (transforms.Normalize) to normalize CIFAR10 dataset tensors using the mean and standard deviation of the dataset

Use TensorFlow Summary File Writer (tf.summary.FileWriter) to create a TensorFlow Summary Event File for TensorBoard

Add a new dimension to the end of a PyTorch tensor by using None-style indexing

Add a new dimension to the middle of a PyTorch tensor by using None-style indexing

Add a new dimension to the beginning of a PyTorch tensor by using None-style indexing

PyTorch numel - Calculate the number of elements in a PyTorch Tensor by using the PyTorch numel operation

Create a PyTorch identity matrix by using the PyTorch eye operation

Use the PyTorch contiguous operation to move a PyTorch Tensor's data to a contiguous chunk of memory

Infer dimensions while reshaping a PyTorch tensor by using the PyTorch view operation

Flatten A PyTorch Tensor by using the PyTorch view operation

PyTorch View - how to use the PyTorch View (.view(...)) operation to reshape a PyTorch tensor

Transpose A Matrix In PyTorch by using the PyTorch T operation

Fill A PyTorch Tensor with a certain scalar by using the PyTorch fill operation

Tell PyTorch to do an in-place operation by using an underscore after an operation's name

Add two PyTorch Tensors together by using the PyTorch add operation

Specify PyTorch Tensor Maximum Value Threshold by using the PyTorch clamp operation

Specify PyTorch Tensor Minimum Value Threshold by using the PyTorch clamp operation

Use PyTorch clamp operation to clip PyTorch Tensor values to a specific range

Generate TensorFlow Tensor full of random numbers in a given range by using TensorFlow's random_uniform operation

Use the TensorFlow reshape operation to infer a tensor's new dimensions when reshaping a tensor

Get the PyTorch Variable shape by using the PyTorch size operation

Calculate the biased standard deviation of all elements in a PyTorch Tensor by using the PyTorch std operation

Calculate the unbiased standard deviation of all elements in a PyTorch Tensor by using the PyTorch std operation

Calculate the power of each element in a PyTorch Tensor for a given exponent by using the PyTorch pow operation

Calculate the Sum of all elements in a tensor by using the PyTorch sum operation

Calculate the Mean value of all elements in a tensor by using the PyTorch mean operation

Use TensorFlow reshape to change the shape of a TensorFlow Tensor as long as the number of elements stay the same

Convert CIFAR10 Dataset from PIL Images to PyTorch Tensors by Using PyTorch's ToTensor Operation

Check for element wise equality between two PyTorch tensors using the PyTorch eq equality comparison operation

tf.matmul - Multiply two matricies by using TensorFlow's matmul operation

Create a PyTorch Tensor full of ones so that each element is a ones using the PyTorch Ones operation

Create a PyTorch Tensor full of zeros so that each element is a zero using the PyTorch Zeros operation

Examine the MNIST dataset from PyTorch Torchvision using Python and PIL, the Python Imaging Library

PyTorch MNIST - Load the MNIST dataset from PyTorch Torchvision and split it into a train data set and a test data set

TensorFlow Element Wise Multiply of Tensors to get the Hadamard product

tf.stack - How to use tf stack operation to stack a list of TensorFlow tensors

PyTorch CIFAR10 - Load CIFAR10 Dataset (torchvision.datasets.cifar10) from Torchvision and split into train and test data sets

TensorFlow Equal - Compare two tensors element wise for equality

tf.ones - How to use tf ones operation to create a TensorFlow ones Tensor

tf.zeros - How to use tf zeros operation to create a TensorFlow zeros Tensor

tf.reduce_sum - Sum Along Axis Using TensorFlow reduce_sum

tf.constant_initializer - Use TensorFlow constant initializer operation to initialize a constant in TensorFlow

tf.variable - TensorFlow variable initialize with NumPy Values by using tf's get_variable operation

tf.constant - Create Tensorflow constant tensor with scalar value using tf constant operation.

TensorFlow Sum - Use TensorFlow's add_n (tf.add_n) to sum list of Tensors

Initialize TensorFlow variables with matrix of your choice. Example with identity matrix.

TensorFlow Identity Matrix Creation with TensorFlow eye (tf.eye)

tf.placeholder - Create A TensorFlow Placeholder Tensor and then when it needs to be evaluated pass a NumPy multi-dimensional array into the feed_dict so that the values are used within the TensorFlow session

TensorFlow squeeze - Use tf.squeeze to remove a dimension from Tensor in order to transfer a 1-D Tensor to a Vector

PyTorch Element Wise Multiplication - Calculate the element wise multiplication to get the Hadamard Product

TensorFlow Add - Use TensorFlow's tf.add to add two Tensors together

get_tensor_by_name - TensorFlow get variable by name by using the TensorFlow get_default_graph operation and then the TensorFlow get_tensor_by_name operation

TensorFlow feed_dict example: Use feed_dict to feed values to TensorFlow placeholders so that you don't run into the error that says you must feed a value for placeholder tensors

PyTorch Tensor Shape - Get the PyTorch Tensor size as a PyTorch Size object and as a list of integers

PyTorch Print Tensor - Print full tensor in PyTorch so that you can see all of the elements rather than just seeing the truncated or shortened version

tf.reduce_mean - Use TensorFlow reduce_mean operation to calculate the mean of tensor elements along various dimensions of the tensor

TensorFlow Initialize Global Variables - Initialize TensorFlow Variables That Depend On Other TensorFlow Variables by using the TensorFlow initialized_value functionality

PyTorch Variable To NumPy - Transform a PyTorch autograd Variable to a NumPy Multidimensional Array by extracting the PyTorch Tensor from the Variable and converting the Tensor to the NumPy array

tf.reduce_max - Calculate the max of a TensorFlow tensor along a certain axis of the tensor using the TensorFlow reduce_max operation

Visualize the training results of running a neural net model with TensorFlow summary and TensorBoard

TensorFlow Max - Use tf.reduce_max to get max value of a TensorFlow Tensor

tf.reshape - Use TensorFlow reshape to convert a tensor to a vector by understanding the two arguments you must pass to the reshape operation and how the special value of negative one flattens the input tensor

Receive the Data Science Weekly Newsletter every Thursday

Easy to unsubscribe at any time. Your e-mail address is safe.