Masking time steps in order to use TCN for variable length sequences about keras-tcn HOT 2 OPEN

@fsbashiri thanks for reporting! I propose an explanation. I'm not 100% sure, you can challenge me.

My clue is the TCN works a bit like an RNN even though it has no states like a LSTM would have.

The last outputs depend on the end of the sequence but also on the beginning.

• If you use post, the end is padded with zeros. The last outputs will be non zeros because they also depend on the beginning of the sequence, which contains values (non zeros).
• Conversely, the first outputs only depends on the beginning of the sequence. If you use pre, the beginning will be padded with 0 and the first outputs will be 0.

For your second point _keras_mask, I guess we should not directly try to call it. But it's strange if it does not exist. Does it exist for other Keras layers that support masking? Maybe we should add it somewhere in the layer because it's not inherited from the Layer object. I don't know.

from keras-tcn.

This problem is mentioned on issue #89. Author states "Con1d by keras lacking supports for Masking layer".

from keras-tcn.