Dropout applied after instead of before the random projection (linear) layer

[sms821]

I needed a small clarification.

In the forward() method of class Conv2dDCLLLayer, dropout has been applied after the linear layer

dcll/dcll/pytorch_libdcll.py

Line 540 in 0618dff

pvoutput = self.dropout(self.i2o(flatten))

This is different from the network described in the paper (Table 2 in https://www.frontiersin.org/articles/10.3389/fnins.2020.00424/full) in which dropout is shown before the linear layer.

Is this intentional? Does the location of dropout have a major effect on network accuracy?

Thanks