Skip to content
Snippets Groups Projects
Commit e3d84dac authored by Alex Zyner's avatar Alex Zyner
Browse files

Removed padding at the end of decoder input, as this caused undesired output

The system was padded with an extra output, weighted zero, to match lengths
between decoder inputs and targets. As the test code creates a longer
output sequence than the training code, any padding is undesirable, and was
removed. This means that a number of refactors took place:

Input data to model renamed from encoder/decoder to observations/future.
This is because the Targets contain the last timestep, and the decoders do
not have the last data point. So the input had to be renamed, as
decoder input = [GO + future[0:-2]] and targets=future[1:-1] so neither
targets nor decoders contained the whole input sequence, as the GO padding
was done at data generation ( not inside the model).

Renaming decoder_inputs meant encoder_inputs were named obersvations for
consistency.

The GO datapoint has also been removed from the graph plot.

I speculate that the padding meant the longer test sequences collapsed.
Testing required.
parent 78b3287d
Branches
No related tags found
No related merge requests found
Loading
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment