未验证 提交 9dc3ed40 编写于 作者: F fengjiayi 提交者: GitHub

Merge pull request #11198 from JiayiFeng/dev_resize_short

Add image_resize_short and refine resize API
......@@ -81,6 +81,8 @@ __all__ = [
'label_smooth',
'roi_pool',
'dice_loss',
'image_resize',
'image_resize_short',
'resize_bilinear',
'gather',
'random_crop',
......@@ -3929,22 +3931,25 @@ def dice_loss(input, label, epsilon=0.00001):
return reduce_mean(dice_score)
def resize_bilinear(input, out_shape=None, scale=None, name=None):
def image_resize(input,
out_shape=None,
scale=None,
name=None,
resample='BILINEAR'):
"""
The mathematical meaning of resize bilinear layer is
Bilinear interpolation.
Bilinear interpolation is an extension of linear interpolation for
interpolating functions of two variables (e.g. H-direction and
W-direction in this layer) on a rectilinear 2D grid.
Resize a batch of images.
For details, please refer to Wikipedia:
https://en.wikipedia.org/wiki/Bilinear_interpolation
The input must be a tensor of the shape (num_batches, channels, in_h, in_w),
and the resizing only applies on the last two dimensions(hight and width).
Supporting resample methods:
'BILINEAR' : Bilinear interpolation
Args:
input (Variable): The input tensor of resize bilinear layer,
input (Variable): The input tensor of image resize layer,
This is a 4-D tensor of the shape
(num_batches, channels, in_h, in_w).
out_shape(list|tuple|Variable|None): Output shape of resize bilinear
out_shape(list|tuple|Variable|None): Output shape of image resize
layer, the shape is (out_h, out_w).
Default: None
scale(float|None): The multiplier for the input height or width.
......@@ -3953,6 +3958,8 @@ def resize_bilinear(input, out_shape=None, scale=None, name=None):
Default: None
name(str|None): A name for this layer(optional). If set None, the layer
will be named automatically.
resample(str): The resample method. It can only be 'BILINEAR' currently.
Default: 'BILINEAR'
Returns:
out (Variable): The output is a 4-D tensor of the shape
......@@ -3961,8 +3968,12 @@ def resize_bilinear(input, out_shape=None, scale=None, name=None):
Examples:
.. code-block:: python
out = fluid.layers.resize_bilinear(input, out_shape=[12, 12])
out = fluid.layers.image_resize(input, out_shape=[12, 12])
"""
resample_methods = {'BILINEAR': 'bilinear_interp'}
if resample not in resample_methods:
raise ValueError(
"The 'resample' of image_resize can only be 'BILINEAR' currently.")
if out_shape is None and scale is None:
raise ValueError("One of out_shape and scale must not be None")
helper = LayerHelper('bilinear_interp', **locals())
......@@ -3990,7 +4001,7 @@ def resize_bilinear(input, out_shape=None, scale=None, name=None):
out = helper.create_tmp_variable(dtype)
helper.append_op(
type="bilinear_interp",
type=resample_methods[resample],
inputs=inputs,
outputs={"Out": out},
attrs={"out_h": out_h,
......@@ -3998,6 +4009,55 @@ def resize_bilinear(input, out_shape=None, scale=None, name=None):
return out
def resize_bilinear(input, out_shape=None, scale=None, name=None):
"""
This is an alias of layer 'image_resize' with bilinear interpolation.
The mathematical meaning of resize bilinear layer is
Bilinear interpolation.
Bilinear interpolation is an extension of linear interpolation for
interpolating functions of two variables (e.g. H-direction and
W-direction in this layer) on a rectilinear 2D grid.
For details, please refer to Wikipedia:
https://en.wikipedia.org/wiki/Bilinear_interpolation
"""
return image_resize(input, out_shape, scale, name, 'BILINEAR')
def image_resize_short(input, out_short_len, resample='BILINEAR'):
"""
Resize a batch of images. The short edge of input images will be
resized to the given 'out_short_len'. The long edge of input images
will be resized proportionately to make images' length-width ratio
constant.
Args:
input (Variable): The input tensor of image resize layer,
This is a 4-D tensor of the shape
(num_batches, channels, in_h, in_w).
out_short_len(int): The length of output images' short edge.
Returns:
out (Variable): The output is a 4-D tensor of the shape
(num_batches, channls, out_h, out_w).
"""
in_shape = input.shape
if len(in_shape) != 4:
raise ValueError(
"The rank of input must be 4 (num_batches, channels, in_h, in_w).")
hw = in_shape[2:4]
short_idx = hw.index(min(hw))
long_idx = 1 - short_idx
out_shape = list(hw)
out_shape[short_idx] = out_short_len
out_shape[long_idx] = int(
float(out_shape[long_idx]) * (float(out_short_len) / float(hw[
short_idx])) + 0.5)
return image_resize(input=input, out_shape=out_shape, resample=resample)
def gather(input, index):
"""
Output is obtained by gathering entries of the outer-most dimension
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册