Basically the model contains Encoder part and Decoder Part so basically the Assignment is to segment unsupervised images using by W-Net Model (The way the paper suggest) , so the output of the model will be
1. Input Image (Original Image )
2. Output of the Encoder part which will be Segmented Image
3. Decoder Part (Which will be the reconstructed image of the Input Image ) so we need to implement the paper b
The paper they develop model called W-Net which is model that the encoder will give you Segmented image while the decoder will reconstructor the input image (original image ) So here is the task using by code you need to do
1. You need to make sure that the model will give good result in this way -- Input Image ===> Segmented Image ==> Reconstructed Image
2. Model Accuracy and Metrics Accuracy ,Plotting the Normalized Cut loss(soft-cut-net-loss & Reconstructed loss (MSE)
3. Latent Vector of segmented image (you have to extract latent vector or embedding of the segmented image while you are training your model )
4. Finalize the result Paper Link :- https://arxiv.org/abs/1711.08506
DescriptionIn this final assignment, the students will demonstrate their ability to apply two ma
Path finding involves finding a path from A to B. Typically we want the path to have certain properties,such as being the shortest or to avoid going t
Develop a program to emulate a purchase transaction at a retail store. Thisprogram will have two classes, a LineItem class and a Transaction class. Th
1 Project 1 Introduction - the SeaPort Project series For this set of projects for the course, we wish to simulate some of the aspects of a number of
1 Project 2 Introduction - the SeaPort Project series For this set of projects for the course, we wish to simulate some of the aspects of a number of