Conv3DTranspose
classkeras.layers.Conv3DTranspose(
filters,
kernel_size,
strides=(1, 1, 1),
padding="valid",
data_format=None,
dilation_rate=(1, 1, 1),
activation=None,
use_bias=True,
kernel_initializer="glorot_uniform",
bias_initializer="zeros",
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=None,
**kwargs
)
3D transposed convolution layer.
The need for transposed convolutions generally arise from the desire to use a transformation going in the opposite direction of a normal convolution, i.e., from something that has the shape of the output of some convolution to something that has the shape of its input while maintaining a connectivity pattern that is compatible with said convolution.
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. When padding="same"
and
strides=1
, the output has the same size as the input."channels_last"
or "channels_first"
.
The ordering of the dimensions in the inputs. "channels_last"
corresponds to inputs with shape
(batch_size, spatial_dim1, spatial_dim2, spatial_dim3, channels)
while "channels_first"
corresponds to inputs with shape
(batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3)
.
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"
.None
, no activation is applied.True
, bias will be added to the output.None
,
the default initializer ("glorot_uniform"
) will be used.None
, the
default initializer ("zeros"
) will be used.Optimizer
(e.g. used to implement
norm constraints or value constraints for layer weights). The
function must take as input the unprojected variable and must return
the projected variable (which must have the same shape). Constraints
are not safe to use when doing asynchronous distributed training.Optimizer
.Input shape
data_format="channels_last"
:
5D tensor with shape:
(batch_size, spatial_dim1, spatial_dim2, spatial_dim3, channels)
data_format="channels_first"
:
5D tensor with shape:
(batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3)
Output shape
data_format="channels_last"
:
5D tensor with shape:
(batch_size, new_spatial_dim1, new_spatial_dim2, new_spatial_dim3,
filters)
data_format="channels_first"
:
5D tensor with shape:
(batch_size, filters, new_spatial_dim1, new_spatial_dim2,
new_spatial_dim3)
Returns
A 5D tensor representing activation(conv3d(inputs, kernel) + bias)
.
Raises
strides > 1
and dilation_rate > 1
.References
Example
>>> x = np.random.rand(4, 10, 8, 12, 128)
>>> y = keras.layers.Conv3DTranspose(32, 2, 2, activation='relu')(x)
>>> print(y.shape)
(4, 20, 16, 24, 32)