A new starter Workflow from Gradient helps you build a web application that can turn a selfie into a deepfaked video of singing an Italian opera song. This tutorial introduces the new starter Workflow.
One of the best ways to learn about convolutional neural networks (CNNs) is to write one from scratch! In this post we look to use PyTorch and the CIFAR-10 dataset to create a new neural network.
In this final part of the six-part series, we recap the main points from the series, and point to next steps, both for this work in terms of other things that Gradient can do, and for the reader who would like to learn more.
In the fifth part of this six-part series, we will show how to deploy the model using Gradient Workflows and its integration with TensorFlow Serving.
In the fourth part of this six-part series, we will improve the result from the model in Part 3 by tuning some of its hyperparameters and demonstrate how the training process can be done in Gradient Workflows.
In the third part of this six-part series, we will use the TensorFlow Recommenders library to build a basic recommender model and train it on the data we prepared in Part 2.
For many organizations, a major question faced by data scientists and engineers is how best to go from the experimentation stage to production. In the second part of a six-part series, we'll show how to go from a raw dataset to a suitable model training set using TensorFlow 2 and Gradient notebooks.
For many organizations, a major question faced by data scientists and engineers is how best to go from the experimentation stage to production. In this first part of six, we outline the most important part of any enterprise data science analysis – posing a business problem.
Paperspace contributor Nigama Vykari guides us through use of the Hough transform feature extraction technique in the context of lane detection for self-driving cars.
