40m QIL Cryo_Lab CTN SUS_Lab TCS_Lab OMC_Lab CRIME_Lab FEA ENG_Labs OptContFac Mariner WBEEShop
  40m Log  Not logged in ELOG logo
Message ID: 14021     Entry time: Tue Jun 26 17:54:59 2018
Author: pooja 
Type: Update 
Category: Cameras 
Subject: Developing neural networks 

Aim:  To find a model that trains the simulated data of Gaussian beam spot moving in a vertical direction by the application of a sinusoidal signal. The data also includes random uniform noise ranging from 0 to 10.

All the attachments are in the zip folder.

I simulated images 128*128 at 10 frames/sec by applying a sine wave of frequency 0.2Hz that moves the beam spot, added random uniform noise ranging from 0 to 10 & resized the image frame using opencv to 64*64. 1000 cycles of this data is taken as train & 300 cycles as test data for the following cases. Optimizer = Nadam (learning rate = 0.001), loss function used = mean squared error, batch size = 32,

Case 1:

Model topology:

                         256 (dropout = 0.1)  ->           256 (dropout = 0.1)   ->       1

Activation :             selu                                         selu

Number of epochs = 240.

Variation in loss value of train & test datasets is given in Attachment 1 of the attached zip folder & the applied signal as well as the output of neural network given in Attachments 2 & 3 (zoomed version of 2).

The model fits well but there is no training since test loss is lower than train loss value. I found in several sites that dropout of some of the nodes during training but retaining them during test could be the probable reason for this (https://stackoverflow.com/questions/48393438/validation-loss-when-using-dropout , http://forums.fast.ai/t/validation-loss-lower-than-training-loss/4581 ). So I removed dropout while training next time.

Case 2:

Model topology:

                         256 (dropout = 0.1)  ->           256 (dropout = 0.1)   ->       1

Activation :             selu                                         selu                          linear

Number of epochs = 200.

Variation in loss value of train & test datasets is given in Attachment 4 of the attached zip folder & the applied signal as well as the output of neural network given in Attachments 5 & 6 (zoomed version of 2).

But still no improvement.

Case 3:

I changed the optimizer to Adam and tried with the same model topology & hyperparameters as case 2 with no success (Attachments 7,8 & 9).

Finally I think this is because I'm training & testing on the same data. So I'm now training with the simulated video but moving it by a maximum of 2 pixels only and testing with a video of ETMY that we had captured earlier.

Attachment 1: NN_noise_diag.zip  971 kB  Uploaded Tue Jun 26 21:03:42 2018
ELOG V3.1.3-