def compute_output_shape(self, input_shape):
if isinstance(input_shape, list):
input_shape = input_shape[0]
cell = self.cell
if cell.data_format == 'channels_first':
rows = input_shape[3]
cols = input_shape[4]
depth = input_shape[5]
elif cell.data_format == 'channels_last':
rows = input_shape[2]
cols = input_shape[3]
depth = input_shape[4]
# rows = conv_utils.conv_output_length(rows,
# cell.kernel_size[0],
# padding=cell.padding,
# stride=cell.strides[0],
# dilation=cell.dilation_rate[0])
# cols = conv_utils.conv_output_length(cols,
# cell.kernel_size[1],
# padding=cell.padding,
# stride=cell.strides[1],
# dilation=cell.dilation_rate[1])
# depth = conv_utils.conv_output_length(depth,
# cell.kernel_size[2],
# padding=cell.padding,
# stride=cell.strides[2],
# dilation=cell.dilation_rate[2])
output_shape = input_shape[:2] + (rows, cols, depth, cell.filters)
output_shape = transpose_shape(output_shape,
cell.data_format,
spatial_axes=(2, 3, 4))
if not self.return_sequences:
output_shape = output_shape[:1] + output_shape[2:]
if self.return_state:
output_shape = [output_shape]
base = (input_shape[0], rows, cols, depth, cell.filters)
base = transpose_shape(base,
cell.data_format,
spatial_axes=(1, 2, 3))
output_shape += [base[:] for _ in range(2)]
return output_shape
def compute_output_shape(self, input_shape):
size_all_dims = (1, ) + self.size + (1, )
spatial_axes = list(range(1, 1 + self.rank))
size_all_dims = transpose_shape(size_all_dims, self.data_format,
spatial_axes)
output_shape = list(input_shape)
for dim in range(len(output_shape)):
if output_shape[dim] is not None:
output_shape[dim] *= size_all_dims[dim]
return tuple(output_shape)
def compute_output_shape(self, input_shape):
padding_all_dims = ((0, 0), ) + self.padding + ((0, 0), )
spatial_axes = list(range(1, 1 + self.rank))
padding_all_dims = transpose_shape(padding_all_dims, self.data_format,
spatial_axes)
output_shape = list(input_shape)
for dim in range(len(output_shape)):
if output_shape[dim] is not None:
output_shape[dim] += sum(padding_all_dims[dim])
return tuple(output_shape)
def spatial_3d_padding(x, padding=((1, 1), (1, 1), (1, 1)), data_format=None):
all_dims_padding = ((0, 0), ) + padding + ((0, 0), )
all_dims_padding = transpose_shape(all_dims_padding,
data_format,
spatial_axes=(1, 2, 3))
return np.pad(x, all_dims_padding, mode='constant')
def spatial_3d_padding(x, padding=((1, 1), (1, 1), (1, 1)), data_format=None):
all_dims_padding = ((0, 0),) + padding + ((0, 0),)
all_dims_padding = transpose_shape(all_dims_padding, data_format,
spatial_axes=(1, 2, 3))
return np.pad(x, all_dims_padding, mode='constant')
