space_to_depth¶

dragon.nn.space_to_depth(
  inputs,
  block_size,
  mode='DCR',
  data_format='NCHW',
  copy=True,
  **kwargs
)[source]¶

Rearrange blocks of spatial data into depth.

Examples:

n, c, h, w, bs = 1, 2, 2, 2, 2
x = dragon.range(n * c * h * w).reshape((n, c, h, w))
y = dragon.reshape(x, (n, c, h // bs, bs, w // bs, bs))
y = dragon.transpose(y, (0, 3, 5, 1, 2, 4))
y = dragon.reshape(y, (n, (bs ** 2) * c, h // bs, w // bs))
z = dragon.nn.space_to_depth(x, 2)  # Equivalent

Parameters:

• inputs (dragon.Tensor) – The input tensor.
• block_size (int, required) – The size of spatial block.
• mode (str, optional, default='DCR') – Rearrangement order for 'NCHW' format.
• data_format (str, optional, default='NCHW') – 'NCHW' or 'NHWC'.
• copy (bool, optional, default=True) – Return a new tensor or call in-place.

Returns:

dragon.Tensor – The output tensor.