MATLAB Answers

0

Why Training Set accuracy decrease dramatically after stopping the trainNetwork?

Asked by Sergy Stepura on 28 Dec 2018
Latest activity Commented on by Don Mathis on 11 Feb 2019
After stopping manually trainNetworktrainNetwork, the validation error dropped dramatically:
I tested the Training Set accuracy, and got also about 60%:
predY = classify(net,xTrain);
Any ideas what I'am doing wrong?

  4 Comments

Show 1 older comment
What is your network architecture? Does it contain dropoutLayers and later BatchNormlization layers?
The network has simple architecture, 5 fully connected layers with batch normalization + Input layer + Output layer (softmax):
1 '' Image Input 120x1x4 images with 'zerocenter' normalization
2 '' Fully Connected 65 fully connected layer
3 '' Batch Normalization Batch normalization
4 '' ReLU ReLU
5 '' Fully Connected 65 fully connected layer
6 '' Batch Normalization Batch normalization
7 '' ReLU ReLU
8 '' Fully Connected 65 fully connected layer
9 '' Batch Normalization Batch normalization
10 '' ReLU ReLU
11 '' Fully Connected 65 fully connected layer
12 '' Batch Normalization Batch normalization
13 '' ReLU ReLU
14 '' Fully Connected 65 fully connected layer
15 '' Batch Normalization Batch normalization
16 '' ReLU ReLU
17 '' Fully Connected 3 fully connected layer
18 '' Softmax softmax
19 '' Classification Output crossentropyex

Sign in to comment.

1 Answer

Answer by Don Mathis on 8 Feb 2019

Maybe your minibatch size is too small. The accuracy drop may be due to batchnormalization layers getting finalized, during which time the mean and variance of the incoming activations of each batchnorm layer are computed using the whole training set. If those full-batch statistics don't match the minibatch statistics very well, the finalized batchnorm layers will not be performing a very good normalization.

  3 Comments

I’m training on 30,000 data set and using batches of 500, do you sugest to use 30,000 batch size?
I’m want to see some stable performance before increasing to full 2,000,000 data set.
You could try increasing the batch size iteratively to see whether that fixes the problem. I would try exponentially increasing: 1000, 2000, 4000, 8000, etc. Or you can just try the largest amount that will fit in your GPU memory right away.
Also: Why does your plot show "Iterations per epoch: 1"? Were you using miniBatchSize=30000 in that run?
What are you passing to trainingOptions()?

Sign in to comment.