Facial Keypoint Detection with PyTorch

Offered By
Coursera Project Network
In this Free Guided Project, you will:

Create Custom dataset for Keypoint problems

Apply Keypoint augmentation and load pretrained model

Create train function and evaluator for training loop

Showcase this hands-on experience in an interview

Clock2 hours
IntermediateIntermediate
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

In this 2-hour project-based course, you will be able to : - Understand the Facial Keypoint Dataset and you will write a custom dataset class for Image-Keypoint dataset. Additionally, you will apply keypoint augmentation to augment images as well as its keypoints. For keypoint augmentation you will use albumentation library. You will plot the image keypoint pair. - Load a pretrained state of the art convolutional neural network using timm library. - Create train function and evaluator function which will helpful to write training loop. Moreover, you will use training loop to train the model. - Lastly, you will use trained model to find keypoints 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

Image ProcessingConvolutional Neural NetworkDeep Learningpytorch

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. Configurations

  2. Understand Facial Keypoint Dataset

  3. Create Custom Facial Keypoint Dataset

  4. Load Dataset into Batches

  5. Create Model

  6. Create Trainer and Evaluator

  7. Training Model

  8. Visualizing Predictions

  9. Optional Task

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

Frequently Asked Questions

More questions? Visit the Learner Help Center.