|TensorFlow 1 version||View source on GitHub|
Masks a sequence by using a mask value to skip timesteps.
Used in the guide:
For each timestep in the input tensor (dimension #1 in the tensor),
if all values in the input tensor at that timestep
are equal to
mask_value, then the timestep will be masked (skipped)
in all downstream layers (as long as they support masking).
If any downstream layer does not support masking yet receives such an input mask, an exception will be raised.
Consider a Numpy data array
x of shape
(samples, timesteps, features),
to be fed to an LSTM layer.
You want to mask timestep #3 and #5 because you lack data for
these timesteps. You can:
x[:, 3, :] = 0.and
x[:, 5, :] = 0.
- Insert a
mask_value=0.before the LSTM layer:
model = Sequential() model.add(Masking(mask_value=0., input_shape=(timesteps, features))) model.add(LSTM(32))
__init__( mask_value=0.0, **kwargs )