Why are the results of forward and predict very different in deep learning?

Question

When I use the "dlnetwork" type deep neural network model to make predictions, the results of the two functions are very different, except that using the predict function will freeze the batchNormalizationLayer and dropout layers.While forward does not freeze the parameters, he is the forward transfer function used in the training phase.     From the two pictures above, there are orders of magnitude difference in the output of the previous 10 results. Where does the problem appear?

Kshitij Singh · Accepted Answer

I ran into this exact problem, and I think I found a solution, I'll discover it when my model finishes training...
 
As others said before, the problem occurs because batchNorms behave differently in forward() and predict(). But there is still a problem here: if you trained your model (forward), it should have converged to a solution that works well in inference (predict), but it doesn't. Something is wrong in the training too.
 
What is wrong is that batchNorms don't update parameters the same way as other layers through (adam/rmsprop/sgdm)update functions. They update through the State property of the dlnetwork object. Consider the code:
 
[gradients,loss] = dlfeval(@modelGradients,dlnet,dlX,Ylabel);
[dlnet,otherOutputs]=rmspropupdate(dlnet,gradients,otherInputs);
function [gradients,loss] = modelGradients(dlnet,dlX,Ylabel)
Y=forward(dlnet,dlX);
loss=myLoss(Y,Ylabel);
gradients=dlgradient(loss,dlnet.Learnables);
end
The code above is wrong if you have batchNorms, it won't update them. The batchNorms are updated through the State property returnet from forward and assigned to dlnet:
[gradients,state,loss] = dlfeval(@modelGradients,dlnet,dlX,Ylabel);
dlnet.State=state; % THIS!!!
[dlnet,otherOutputs]=rmspropupdate(dlnet,gradients,otherInputs);
function [gradients,state,loss] = modelGradients(dlnet,dlX,Ylabel)
[Y,state]=forward(dlnet,dlX); % THIS!!!
loss=myLoss(Y,Ylabel);
gradients=dlgradient(loss,dlnet.Learnables);
end
Now that dlnet has a State property updated at every forward() call, the batchNorms are updated and your model should converge to a solution that works for predict().
 
I would also like caling MathWorks attention that this detail is only present in documentation in ONE example of GAN networks (in spite of the omnipresence of batchNorm layers in deep learning models) and is never mentioned explicitly.

Why are the results of forward and predict very different in deep learning?

Need a Custom Version or Complete Simulation for This Problem?

how can I overcome on algebraic loop in simulink

How to create an attention layer for deep learning networks?

How do I generate a pulse train which starts at the origin using functions

Nvidia NVLink in MATALB using multiple Geforce 2080 ti cards

How to train labels for image blocks using neural network?

Using a python trained neural network

Modeling and Simulation of an Induction Motor Using Sliding Mode Control in MATLAB

Solar Inverter with BMS in MATLAB Simulink Complete Simulation Project

Simulation and Kinematic Analysis of a 5-DOF RRRRRP Robotic Manipulator Using MATLAB

Get a Free Consultation or a Sample Assignment Review!