Transposed convolutional layer (sometimes called Deconvolution).
The need for transposed convolutions generally arises
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.
When using this layer as the first layer in a model, provide the
configuration inputShape (Array of integers, does not include the
sample axis), e.g., inputShape: [128, 128, 3] for 128x128 RGB pictures in
dataFormat: 'channelsLast'.
Input shape:
4D tensor with shape:
[batch, channels, rows, cols] if dataFormat is 'channelsFirst'.
or 4D tensor with shape
[batch, rows, cols, channels] if dataFormat is 'channelsLast'.
Output shape:
4D tensor with shape:
[batch, filters, newRows, newCols] if dataFormat is
'channelsFirst'. or 4D tensor with shape:
[batch, newRows, newCols, filters] if dataFormat is 'channelsLast'.
Transposed convolutional layer (sometimes called Deconvolution).
The need for transposed convolutions generally arises 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.
When using this layer as the first layer in a model, provide the configuration
inputShape(Arrayof integers, does not include the sample axis), e.g.,inputShape: [128, 128, 3]for 128x128 RGB pictures indataFormat: 'channelsLast'.Input shape: 4D tensor with shape:
[batch, channels, rows, cols]ifdataFormatis'channelsFirst'. or 4D tensor with shape[batch, rows, cols, channels]ifdataFormatis'channelsLast'.Output shape: 4D tensor with shape:
[batch, filters, newRows, newCols]ifdataFormatis'channelsFirst'. or 4D tensor with shape:[batch, newRows, newCols, filters]ifdataFormatis'channelsLast'.References: