DL_ICP 6 - Saiaishwaryapuppala/CSEE5590_python_Icp GitHub Wiki

Python and Deep Learning: Special Topics

Rajeshwari Sai Aishwarya Puppala

Student ID: 16298162

Class ID: 35

Deep Learning-In class programming:6

Objectives

  1. Add one more hidden layer to autoencoder

  2. Do the prediction on the test data and then visualize one of the reconstructed version of that test data. Also, visualize the same test data before reconstructionusing Matplotlib

  3. Repeat the question 2 on the denoisening autoencoder

  4. Plot loss and accuracy using the history object

Import Statements

Import all the packages required for this usecase

Model1 with Hidden Layer

  • Add one more hidden layer to autoencoder.
  • From the above code one hidden layer is added to the side of encoder and one to the side of decoder.

Dataset Division & Fit Data

Divide the dataset into train and test data and fit the model.

Visualize the Input and Reconstructed representation of Images

The input and reconstructed representation of the autoencoder.

Results

Loss and Accuracy Plot

Accuracy

Loss

Add Noisy Factor and fitting data

Visualizing the Input and Reconstructed representation of Images

  • The input and noisy images and noisy reconstructed representation of the autoencoder.

Result

Accuracy and Loss plot

Accuracy plot

Loss Plot