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....
The project was extremely useful to apply the knowledge in real world applications in the field of advanced computer vision. The instructor did a nice job and explained most of the concepts very clear.