AA
4 because there were quite a few mistakes which should be corrected!
In this 2-hour project-based course, you will be able to :
- Understand the Massachusetts Roads Segmentation Dataset and you will write a custom dataset class for Image-mask dataset. Additionally, you will apply segmentation domain augmentations to augment images as well as its masks. For image-mask augmentation you will use albumentation library. You will plot the image-Mask pair. - Load a pretrained state of the art convolutional neural network for segmentation problem(for e.g, Unet) using segmentation model pytorch library. - Create train function and evaluator function which will helpful to write training loop. Moreover, you will use training loop to train the model. - Finally, we will use best trained segementation model for inference.
AA
4 because there were quite a few mistakes which should be corrected!
Showing: 6 of 6
I like it much
Worst Course ever. There is no explanation of Code and also not a tiny bit of theory. Instructor just read the code while coding like a memorized machine.
Πολύ καλό μάθημα.
The project is explained step by step with good didactics; however, I notice that there is no assistance beyond the video, and the unanswered forums of questions.
4 because there were quite a few mistakes which should be corrected!
i needed more graded quizes