How can I increase the accuracy score for my autoencoder neural network?

Question

0.00/5 (No votes)

See more:

, +

I tried to make a UNet based Autoencoder for the purpose of De-blurring images but I got terrible accuracy scores and loss values. How can I improve the model ?

The code for the model is HERE

What I have tried:

I tried to vary the learning rate, the size of input images, batch normalization.

Posted 24-Aug-20 3:20am

Aryan Sethi

Updated 24-Aug-20 3:43am

Add a Solution

1 solution

Add a Solution

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

Gerry Schmitz · Answer 1 · 2020-08-24T03:44:00

Solution 1

Can't see how ML can help you much; it's more about algorithms (light intensity; contrast; etc.).

Deblurring Images Using the Blind Deconvolution Algorithm- MATLAB & Simulink Example[^]

Posted 24-Aug-20 3:44am

Gerry Schmitz

Comments

Aryan Sethi 24-Aug-20 13:37pm

I've seen multiple people trying the same thing using AutoEncoders with significant accuracies.

[no name] 28-Aug-20 19:54pm

Why don't you ask them then?

How can I increase the accuracy score for my autoencoder neural network?

1 solution

Solution 1

Add your solution here

Preview 0

How can I increase the accuracy score for my autoencoder neural network?

1 solution

Solution 1

Add your solution here

Preview 0

Existing Members

...or Join us