Coursera MOOC / Non-credit 0

Deep Learning with PyTorch : GradCAM

Name: Deep Learning with PyTorch : GradCAM
Price: 9.99 USD
Availability: InStock

About this course

Gradient-weighted Class Activation Mapping (Grad-CAM), uses the class-specific gradient information flowing into the final convolutional layer of a CNN to produce a coarse localization map of the important regions in the image. In this 2-hour long project-based course, you will implement GradCAM on simple classification dataset. You will write a custom dataset class for Image-Classification dataset. Thereafter, you will create custom CNN architecture. Moreover, you are going to create train function and evaluator function which will be helpful to write the training loop. After, saving the best model, you will write GradCAM function which return the heatmap of localization map of a given class. Lastly, you plot the heatmap which the given input image.

56/100

CourseAsk score

What the provider tells you: 32/45
Who stands behind it: 8/35
How complete the listing is: 16/20

Scores how much the provider publishes and who stands behind it — not how well it is taught.

What you'll learn

implement Grad-CAM for CNNs
create custom dataset and CNN architecture
write functions for training and evaluating models
generate and plot heatmaps of important image regions

Deep Learning #deep learning #machine learning #model evaluation #computer vision #data science #pytorch #image classification #visualization #cnn #grad-cam

$9.99

Price shown by Coursera — confirm on their site.

Enroll on Coursera

You'll be redirected to Coursera to complete enrollment.