image_resize
注意: 参数 actual_shape
将被弃用,请使用 out_shape
替代。
该OP用于调整一个batch中图片的大小。
输入为4-D Tensor时形状为(num_batches, channels, in_h, in_w)或者(num_batches, in_h, in_w, channels),输入为5-D Tensor时形状为(num_batches, channels, in_d, in_h, in_w)或者(num_batches, in_d, in_h, in_w, channels),并且调整大小只适用于深度,高度和宽度对应的维度。
支持的插值方法:
最近邻插值是在输入张量的高度和宽度上进行最近邻插值。
双线性插值是线性插值的扩展,用于在直线2D网格上插值两个变量(例如,该操作中的H方向和W方向)的函数。 关键思想是首先在一个方向上执行线性插值,然后在另一个方向上再次执行线性插值。
三线插值是线性插值的一种扩展,是3参数的插值方程(比如op里的D,H,W方向),在三个方向上进行线性插值。
Align_corners和align_mode是可选参数,插值的计算方法可以由它们选择。
有关最近邻插值的详细信息,请参阅维基百科: https://en.wikipedia.org/wiki/Nearest-neighbor_interpolation
有关双线性插值的详细信息,请参阅维基百科:
有关三线插值的详细信息,请参阅维基百科: https://en.wikipedia.org/wiki/Trilinear_interpolation
4-D Tensor,形状为 (num_batches, channels, out_h, out_w) 或 (num_batches, out_h, out_w, channels);或者5-D Tensor,形状为 (num_batches, channels, out_d, out_h, out_w) 或 (num_batches, out_d, out_h, out_w, channels)。
import paddle.fluid as fluid
input = fluid.layers.data(name="input", shape=[3,6,9], dtype="float32")
# input.shape = [-1, 3, 6, 9], where -1 indicates batch size, and it will get the exact value in runtime.
out = fluid.layers.image_resize(input, out_shape=[12, 12], resample="NEAREST")
out0 = fluid.layers.image_resize(input, out_shape=[12, 12], resample="NEAREST")
# out0.shape = [-1, 3, 12, 12], it means out0.shape[0] = input.shape[0] in runtime.
# out_shape is a list in which each element is a integer or a tensor Variable
out1 = fluid.layers.image_resize(input, out_shape=[12, dim1], resample="NEAREST")
# out_shape is a 1-D tensor Variable
shape_tensor = fluid.layers.data(name="shape_tensor", shape=[2], dtype="int32", append_batch_size=False)
out2 = fluid.layers.image_resize(input, out_shape=shape_tensor, resample="NEAREST")
# out2.shape = [-1, 3, -1, -1]
# when use actual_shape
actual_shape_tensor = fluid.layers.data(name="actual_shape_tensor", shape=[2], dtype="int32", append_batch_size=False)
out3 = fluid.layers.image_resize(input, out_shape=[4, 4], resample="NEAREST", actual_shape=actual_shape_tensor)
# out3.shape = [-1, 3, 4, 4]
# scale is a Variable
scale_tensor = fluid.layers.data(name="scale", shape=[1], dtype="float32", append_batch_size=False)
out4 = fluid.layers.image_resize(input, scale=scale_tensor)