Deep Learning with PyTorch : Object Localization

4.7
stars

19 ratings

Offered By

2,812 already enrolled

In this Free Guided Project, you will:

Create custom dataset for Localization problems

Apply augmentations for localization task and load pretrained model

Create train function and evaluator for training loop

Showcase this hands-on experience in an interview

2 hours
Intermediate
No download needed
Split-screen video
English
Desktop only

Object Localization is the task of locating an instance of a particular object category in an image, typically by specifying a tightly cropped bounding box centered on the instance. In this 2-hour project-based course, you will be able to understand the Object Localization Dataset and you will write a custom dataset class for Image-bounding box dataset. Additionally, you will apply augmentation for localization task to augment images as well as its effect on bounding box. For localization task augmentation you will use albumentation library. We will plot the (image-bounding box) pair. Thereafter, we will load a pretrained state of the art convolutional neural network using timm library.Moreover, we are going to create train function and evaluator function which will be helpful to write training loop. Lastly, you will use best trained model to find bounding box given any image.

Requirements

Prior programming experience in Python and basic pytorch. Theoretical knowledge of Convolutional Neural Network and Training process (Optimization)

Skills you will develop

  • Deep Learning

  • Object Localization

  • Convolutional Neural Network

  • pytorch

  • Image Processing

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Set up colab run environment

  2. Configurations

  3. Understand the dataset

  4. Augmentations

  5. Create Custom Dataset

  6. Load dataset into batches

  7. Create Model

  8. Create Train and Eval Functions

  9. Training Loop

  10. Inference

How Guided Projects work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Frequently Asked Questions

Because your workspace contains a cloud desktop that is sized for a laptop or desktop computer, Guided Projects are not available on your mobile device.

Guided Project instructors are subject matter experts who have experience in the skill, tool or domain of their project and are passionate about sharing their knowledge to impact millions of learners around the world.

You can download and keep any of your created files from the Guided Project. To do so, you can use the “File Browser” feature while you are accessing your cloud desktop.

At the top of the page, you can press on the experience level for this Guided Project to view any knowledge prerequisites. For every level of Guided Project, your instructor will walk you through step-by-step.

Yes, everything you need to complete your Guided Project will be available in a cloud desktop that is available in your browser.

You'll learn by doing through completing tasks in a split-screen environment directly in your browser. On the left side of the screen, you'll complete the task in your workspace. On the right side of the screen, you'll watch an instructor walk you through the project, step-by-step.