From the course: Computer Vision for Data Scientists
Unlock the full course today
Join today to access over 24,200 courses taught by industry experts.
The trainer
From the course: Computer Vision for Data Scientists
The trainer
- [Instructor] Now that you've got an overview of SuperGradients, let's see it in action. So this notebook that you have available to you should look a bit familiar. The first few cells in this notebook are the exact same as the PyTorch crash course. What this is doing is downloading the dataset and then splitting the dataset into the train, validation, and test sets. Once that's been done, we're instantiating our DataLoaders. Now, SuperGradients is a PyTorch based training library. That means you can use your PyTorch DataLoaders as is without having to do anything extra, and that's a nice feature to have. So we'll instantiate our PyTorch DataLoaders using the ImageFolder format. Once we've done that, we can start installing SuperGradients. So it's important to pin the version of SuperGradients, so that you can reproduce the results that I have here. So if you're watching this at some point in the future, make sure that…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
-
-
-
-
-
(Locked)
Introduction to SuperGradients2m 21s
-
(Locked)
The trainer4m 14s
-
(Locked)
Required training params3m 50s
-
(Locked)
Optional training params6m 39s
-
(Locked)
Training the model3m 13s
-
(Locked)
Predicting with the model4m 28s
-
(Locked)
How to solve almost any image classification problem with SG6m 19s
-
(Locked)
-
-