resize_bilinear

paddle.fluid.layers.nn. resize_bilinear ( input, out_shape=None, scale=None, name=None, actual_shape=None, align_corners=True, align_mode=1, data_format='NCHW' ) [source]

This op resizes the input by performing bilinear interpolation based on given output shape which specified by actual_shape, out_shape and scale in priority order.

Warning: the parameter actual_shape will be deprecated in the future and only use out_shape instead.

Bilinear interpolation is an extension of linear interpolation for interpolating functions of two variables (e.g. H-direction and W-direction in this op) on a rectilinear 2D grid. The key idea is to perform linear interpolation first in one direction, and then again in the other direction.

For details of bilinear interpolation, please refer to Wikipedia: https://en.wikipedia.org/wiki/Bilinear_interpolation

Align_corners and align_mode are optional parameters,the calculation method of interpolation can be selected by them.

Example:

For scale:

    if align_corners = True && out_size > 1 :

      scale_factor = (in_size-1.0)/(out_size-1.0)

    else:

      scale_factor = float(in_size/out_size)

Bilinear interpolation:

  if:
      align_corners = False , align_mode = 0

      input : (N,C,H_in,W_in)
      output: (N,C,H_out,W_out) where:

      H_out = (H_{in}+0.5) * scale_{factor} - 0.5
      W_out = (W_{in}+0.5) * scale_{factor} - 0.5

  else:

      input : (N,C,H_in,W_in)
      output: (N,C,H_out,W_out) where:
      H_out = H_{in} * scale_{factor}
      W_out = W_{in} * scale_{factor}
Parameters

  • input (Variable) – 4-D Tensor(NCHW), its data type is float32, float64, or uint8, its data format is specified by data_format.

  • out_shape (list|tuple|Variable|None) – Output shape of resize bilinear layer, the shape is (out_h, out_w).Default: None. If a list, each element can be an integer or a Tensor Variable with shape: [1]. If a Tensor Variable, its dimension size should be 1.

  • scale (float|Variable|None) – The multiplier for the input height or width. At least one of out_shape or scale must be set. And out_shape has a higher priority than scale. Default: None.

  • actual_shape (Variable) – An optional input to specify output shape dynamically. If provided, image resize according to this given shape rather than out_shape and scale specifying shape. That is to say actual_shape has the highest priority. It is recommended to use out_shape if you want to specify output shape dynamically, because actual_shape will be deprecated. When using actual_shape to specify output shape, one of out_shape and scale should also be set, otherwise errors would be occurred in graph constructing stage. Default: None

  • align_corners (bool) – an optional bool. Defaults to True. If True, the centers of 4 corner pixels of the input and output tensors are aligned, preserving the values at the corner pixels, If False, are not aligned

  • align_mode (bool) – (int, default ‘1’), optional for bilinear interpolation, can be ‘0’ for src_idx = scale*(dst_indx+0.5)-0.5 , can be ‘1’ for src_idx = scale*dst_index

  • data_format (str, optional) – Specify the data format of the input, and the data format of the output will be consistent with that of the input. An optional string from: “NCHW”, “NHWC”. The default is “NCHW”. When it is “NCHW”, the data is stored in the order of: [batch_size, input_channels, input_height, input_width].

  • name (str, optional) – The default value is None. Normally there is no need for user to set this property. For more information, please refer to Name

Returns

4-D tensor(NCHW or NHWC).

Return type

Variable

Examples

#declarative mode
import paddle.fluid as fluid
import numpy as np
import paddle
paddle.enable_static()
input = fluid.data(name="input", shape=[None,3,6,10])

#1
output = fluid.layers.resize_bilinear(input=input,out_shape=[12,12])

#2
#x = np.array([2]).astype("int32")
#dim1 = fluid.data(name="dim1", shape=[1], dtype="int32")
#fluid.layers.assign(input=x, output=dim1)
#output = fluid.layers.resize_bilinear(input=input,out_shape=[12,dim1])

#3
#x = np.array([3,12]).astype("int32")
#shape_tensor = fluid.data(name="shape_tensor", shape=[2], dtype="int32")
#fluid.layers.assign(input=x, output=shape_tensor)
#output = fluid.layers.resize_bilinear(input=input,out_shape=shape_tensor)

#4
#x = np.array([0.5]).astype("float32")
#scale_tensor = fluid.data(name="scale", shape=[1], dtype="float32")
#fluid.layers.assign(x,scale_tensor)
#output = fluid.layers.resize_bilinear(input=input,scale=scale_tensor)

place = fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())

input_data = np.random.rand(2,3,6,10).astype("float32")

output_data = exe.run(fluid.default_main_program(),
    feed={"input":input_data},
    fetch_list=[output],
    return_numpy=True)

print(output_data[0].shape)

#1
# (2, 3, 12, 12)
#2
# (2, 3, 12, 2)
#3
# (2, 3, 3, 12)
#4
# (2, 3, 3, 5)

#imperative mode
import paddle.fluid.dygraph as dg

with dg.guard(place) as g:
    input = dg.to_variable(input_data)
    output = fluid.layers.resize_bilinear(input=input, out_shape=[12,12])
    print(output.shape)

    # [2L, 3L, 12L, 12L]