ConvLSTM3D
classkeras.layers.ConvLSTM3D(
filters,
kernel_size,
strides=1,
padding="valid",
data_format=None,
dilation_rate=1,
activation="tanh",
recurrent_activation="sigmoid",
use_bias=True,
kernel_initializer="glorot_uniform",
recurrent_initializer="orthogonal",
bias_initializer="zeros",
unit_forget_bias=True,
kernel_regularizer=None,
recurrent_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
recurrent_constraint=None,
bias_constraint=None,
dropout=0.0,
recurrent_dropout=0.0,
seed=None,
return_sequences=False,
return_state=False,
go_backwards=False,
stateful=False,
**kwargs
)
3D Convolutional LSTM.
Similar to an LSTM layer, but the input transformations and recurrent transformations are both convolutional.
Arguments
strides > 1
is incompatible with
dilation_rate > 1
."valid"
or "same"
(case-insensitive).
"valid"
means no padding. "same"
results in padding evenly to
the left/right or up/down of the input such that output has the same
height/width dimension as the input."channels_last"
or "channels_first"
.
The ordering of the dimensions in the inputs. "channels_last"
corresponds to inputs with shape (batch, steps, features)
while "channels_first"
corresponds to inputs with shape
(batch, features, steps)
. It defaults to the image_data_format
value found in your Keras config file at ~/.keras/keras.json
.
If you never set it, then it will be "channels_last"
.tanh(x)
).kernel
weights matrix,
used for the linear transformation of the inputs.recurrent_kernel
weights
matrix, used for the linear transformation of the recurrent state.True
, add 1 to the bias of the forget
gate at initialization.
Use in combination with bias_initializer="zeros"
.
This is recommended in Jozefowicz et al., 2015kernel
weights
matrix.recurrent_kernel
weights matrix.kernel
weights
matrix.recurrent_kernel
weights matrix.False
.False
.False
).
If True
, process the input sequence backwards and return the
reversed sequence.True
, the last state
for each sample at index i in a batch will be used as initial
state for the sample of index i in the following batch.False
).
If True
, the network will be unrolled,
else a symbolic loop will be used.
Unrolling can speed-up a RNN,
although it tends to be more memory-intensive.
Unrolling is only suitable for short sequences.Call arguments
(samples, timesteps)
indicating whether a
given timestep should be masked.dropout
or recurrent_dropout
are set.Input shape
data_format='channels_first'
:
5D tensor with shape: (samples, time, channels, *spatial_dims)
data_format='channels_last'
:
5D tensor with shape: (samples, time, *spatial_dims, channels)
Output shape
return_state
: a list of tensors. The first tensor is the output.
The remaining tensors are the last states,
each 4D tensor with shape: (samples, filters, *spatial_dims)
if
data_format='channels_first'
or shape: (samples, *spatial_dims, filters)
if
data_format='channels_last'
.return_sequences
: 5D tensor with shape: (samples, timesteps,
filters, *spatial_dims)
if data_format='channels_first'
or shape: (samples, timesteps, *spatial_dims, filters)
if
data_format='channels_last'
.(samples, filters, *spatial_dims)
if
data_format='channels_first'
or shape: (samples, *spatial_dims, filters)
if
data_format='channels_last'
.References