# conv3d_transpose¶

dragon.vm.tensorflow.nn.conv3d_transpose(
input,
filters,
output_shape=None,
strides=1,
data_format='NHWC',
dilations=None,
name=None
)[source]

Apply the 3d deconvolution.

• If data_format is 'NCHW', excepts input shape $$(N, C_{\text{in}}, D, H, W)$$, filters shape $$(C_{\text{in}}, C_{\text{out}}, D_{\text{f}}, H_{\text{f}}, W_{\text{f}})$$, and output shape is $$(N, C_{\text{out}}, D_{\text{out}}, H_{\text{out}}, W_{\text{out}})$$.
• If data_format is 'NHWC', excepts input shape $$(N, D, H, W, C_{\text{in}})$$, filters shape $$(C_{\text{in}}, D_{\text{f}}, H_{\text{f}}, W_{\text{f}}, C_{\text{out}})$$, and output shape is $$(N, D_{\text{out}}, H_{\text{out}}, W_{\text{out}}, C_{\text{out}})$$.
• padding could be 'VALID', 'SAME' or explicit padding size.

Examples:

x = tf.ones((1, 2, 2, 2, 2))
filters = tf.ones((3, 1, 1, 1, 2))
y = tf.nn.conv3d_transpose(x, filters, output_shape=(2, 2, 2))
assert y.shape == (1, 2, 2, 2, 3)

Parameters:
• input (dragon.Tensor) – The input tensor.
• filters (dragon.Tensor) – The filters tensor.
• output_shape (Union[Sequence[int], dragon.Tensor], optional) – The optional output shape.
• strides (Union[int, Sequence[int]], default=1) – The stride of convolution window.
• data_format (str, optional, default='NHWC') – 'NCHW' or 'NHWC'.