megengine.functional.nn.conv_transpose3d

conv_transpose3d(inp, weight, bias=None, stride=1, padding=0, dilation=1)

3D transposed convolution operation. Only support the case that groups = 1 and conv_mode = “cross_correlation”.

Refer to ConvTranspose3d for more information.

参数

• inp (Tensor) – 卷积运算的特征图。

• weight (Tensor) – convolution kernel. weight usually has shape (in_channels, out_channels, depth, height, width).

• bias (Optional[Tensor]) – 添加到卷积结果中的偏置量(如果给定该值)

• stride (Union[int, Tuple[int, int, int]]) – 三维卷积运算中的步长。 默认： 1

• padding (Union[int, Tuple[int, int, int]]) – size of the paddings added to the input on all sides of its spatial dimensions. Only zero-padding is supported. Default: 0

• dilation (Union[int, Tuple[int, int, int]]) – 三维卷积运算的扩张值(dilation)。 默认： 1

返回类型

Tensor

返回

输出张量。

上一页

megengine.functional.nn.conv_transpose2d

下一页

megengine.functional.nn.deformable_conv2d