megengine.module.SlidingWindowTranspose¶

class SlidingWindowTranspose(output_size, kernel_size, padding=0, stride=1, dilation=1, **kwargs)[源代码]¶

Opposite opration of SlidingWindow, sum over the sliding windows on the corresponding input location. Given an input of the size \((N, C, IH, IW, window_h, window_w)\) and output_size, the output shape would be \((N, C, output\_size_{h}, output\_size_{w})\) and the arguments must satisfy

\[\text{IH} = \lfloor \frac{\text{output_size}_{h} + 2 * \text{padding}_{h} - \text{dilation}_{h} * (\text{kernel_size}_{h} - 1) - 1}{\text{stride}_{h}} + 1 \rfloor\]

\[\text{IW} = \lfloor \frac{\text{output_size}_{w} + 2 * \text{padding}_{w} - \text{dilation}_{w} * (\text{kernel_size}_{w} - 1) - 1}{\text{stride}_{w}} + 1 \rfloor\]

For each output location, we have:

\[\text{out}_{n, c, oh, ow} = \sum_{n,c,oh,ow=location(n, c, ih, iw, wh, ww)}\text{src}_{n, c, ih, iw, wh, ww}\]

\[\begin{split}\text{location}(n, c, ih, iw, wh, ww) &= (n, c, oh+wh, ow+ww) \\ \text{where } & oh=-pad_h+ih \times stride_h + (wh-1) \times (dilation_h-1) \\ & ow=-pad_w+iw \times stride_w + (ww-1) \times (dilation_w-1)\end{split}\]

参数

output_size (Union[int, Tuple[int, int]]) – the size of the output tensor.
kernel_size (Union[int, Tuple[int, int]]) – the size of the window to take a max over.
padding (Union[int, Tuple[int, int]]) – implicit zero padding to be added on both sides. Default: 0
stride (Union[int, Tuple[int, int]]) – the stride of the window. Default: 1
dilation (Union[int, Tuple[int, int]]) – the dilation of the window. Default: 1

Methods

`apply`(fn)	Applies function `fn` to all the modules within this module, including itself.
`buffers`([recursive])	Returns an iterable for the buffers of the module.
`children`(**kwargs)	Returns an iterable for all the submodules that are direct attributes of this module.
`disable_quantize`([value])	Sets `module`'s `quantize_disabled` attribute and return `module`.
`eval`()	Sets training mode of all the modules within this module (including itself) to `False`.
`forward`(inp)
`load_state_dict`(state_dict[, strict])	Loads a given dictionary created by `state_dict` into this module.
`modules`(**kwargs)	Returns an iterable for all the modules within this module, including itself.
`named_buffers`([prefix, recursive])	Returns an iterable for key buffer pairs of the module, where `key` is the dotted path from this module to the buffer.
`named_children`(**kwargs)	Returns an iterable of key-submodule pairs for all the submodules that are direct attributes of this module, where 'key' is the attribute name of submodules.
`named_modules`([prefix])	Returns an iterable of key-module pairs for all the modules within this module, including itself, where 'key' is the dotted path from this module to the submodules.
`named_parameters`([prefix, recursive])	Returns an iterable for key `Parameter` pairs of the module, where `key` is the dotted path from this module to the `Parameter`.
`named_tensors`([prefix, recursive])	Returns an iterable for key tensor pairs of the module, where `key` is the dotted path from this module to the tensor.
`parameters`([recursive])	Returns an iterable for the `Parameter` of the module.
`register_forward_hook`(hook)	Registers a hook to handle forward results.
`register_forward_pre_hook`(hook)	Registers a hook to handle forward inputs.
`replace_param`(params, start_pos[, seen])	Replaces module's parameters with `params`, used by `ParamPack` to
`state_dict`([rst, prefix, keep_var])
`tensors`([recursive])	Returns an iterable for the `Tensor` of the module.
`train`([mode, recursive])	Sets training mode of all the modules within this module (including itself) to `mode`.
`zero_grad`()	Sets all parameters' grads to zero

megengine.module.SlidingWindow.zero_grad

megengine.module.SlidingWindowTranspose.apply