Deep Learning with PyTorch : GradCAM
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.
Buy Now Free
- Level Professional
- المدة 3 ساعات hours
- الطبع بواسطة Coursera Project Network
-
Offered by
عن
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.الوحدات
Your Learning Journey
-
1
Readings
-
1
Plugin
-
1
Lab
-
1
Assignment
1
Assignment
- Assess Your Knowledge
1
Labs
- Deep Learning with PyTorch : GradCAM
1
Readings
- Project Overview
Auto Summary
Deep Learning with PyTorch: GradCAM is an intermediate-level, 2-hour project-based course focused on Gradient-weighted Class Activation Mapping (Grad-CAM) in CNNs. Offered by Coursera, it guides learners through implementing GradCAM on a classification dataset, creating custom datasets, CNN architectures, and training loops, and visualizing heatmaps. Available for free, this course is ideal for IT and Computer Science enthusiasts seeking hands-on experience with PyTorch.
Parth Dhameliya