mxnet.ndarray.UpSampling¶

mxnet.ndarray.UpSampling(*data, **kwargs)¶

Performs nearest neighbor/bilinear up sampling to inputs.

Parameters

data (NDArray[]) – Array of tensors to upsample
scale (int, required) – Up sampling scale
num_filter (int, optional, default='0') – Input filter. Only used by bilinear sample_type.
sample_type ({'bilinear', 'nearest'}, required) – upsampling method
multi_input_mode ({'concat', 'sum'},optional, default='concat') – How to handle multiple input. concat means concatenate upsampled images along the channel dimension. sum means add all images together, only available for nearest neighbor upsampling.
workspace (long (non-negative), optional, default=512) – Tmp workspace for deconvolution (MB)
out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays