Project objectives:
-
Understand the Segmentation Dataset and write a custom dataset class for Image-Mask dataset.
-
Apply segmentation augmentation to augment images as well as their masks. For image-mask augmentation, use albumentation library, then plot the image-mask pair.
-
Load a pre-trained state-of-the art convolutional neural network for segmentation problems (e.g., U-net) using segmentation model in PyTorch library.
-
Create a train and evaluate function which is helpful to use training loop to train the model.