Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
PaddlePaddle
Paddle
提交
4f54891c
P
Paddle
项目概览
PaddlePaddle
/
Paddle
大约 1 年 前同步成功
通知
2298
Star
20931
Fork
5422
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1423
列表
看板
标记
里程碑
合并请求
543
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
1,423
Issue
1,423
列表
看板
标记
里程碑
合并请求
543
合并请求
543
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
未验证
提交
4f54891c
编写于
9月 01, 2021
作者:
L
LielinJiang
提交者:
GitHub
9月 01, 2021
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add input and output description docs for vision transform (#34926)
* add input and output docs for vision transform
上级
5eefc8c7
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
128 addition
and
11 deletion
+128
-11
python/paddle/vision/transforms/transforms.py
python/paddle/vision/transforms/transforms.py
+128
-11
未找到文件。
python/paddle/vision/transforms/transforms.py
浏览文件 @
4f54891c
...
...
@@ -309,7 +309,14 @@ class ToTensor(BaseTransform):
data_format (str, optional): Data format of output tensor, should be 'HWC' or
'CHW'. Default: 'CHW'.
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray): The input image with shape (H x W x C).
- output(np.ndarray): A tensor with shape (C x H x W) or (H x W x C) according option data_format.
Returns:
A callable object of ToTensor.
Examples:
.. code-block:: python
...
...
@@ -368,6 +375,13 @@ class Resize(BaseTransform):
- "lanczos": cv2.INTER_LANCZOS4
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): A resized image.
Returns:
A callable object of Resize.
Examples:
.. code-block:: python
...
...
@@ -422,6 +436,13 @@ class RandomResizedCrop(BaseTransform):
- "lanczos": cv2.INTER_LANCZOS4
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): A cropped image.
Returns:
A callable object of RandomResizedCrop.
Examples:
.. code-block:: python
...
...
@@ -503,6 +524,13 @@ class CenterCrop(BaseTransform):
size (int|list|tuple): Target size of output image, with (height, width) shape.
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): A cropped image.
Returns:
A callable object of CenterCrop.
Examples:
.. code-block:: python
...
...
@@ -537,6 +565,13 @@ class RandomHorizontalFlip(BaseTransform):
prob (float, optional): Probability of the input data being flipped. Should be in [0, 1]. Default: 0.5
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): A horiziotal flipped image.
Returns:
A callable object of RandomHorizontalFlip.
Examples:
.. code-block:: python
...
...
@@ -571,6 +606,13 @@ class RandomVerticalFlip(BaseTransform):
prob (float, optional): Probability of the input data being flipped. Default: 0.5
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): A vertical flipped image.
Returns:
A callable object of RandomVerticalFlip.
Examples:
.. code-block:: python
...
...
@@ -579,7 +621,7 @@ class RandomVerticalFlip(BaseTransform):
from PIL import Image
from paddle.vision.transforms import RandomVerticalFlip
transform = RandomVerticalFlip(
224
)
transform = RandomVerticalFlip()
fake_img = Image.fromarray((np.random.rand(300, 320, 3) * 255.).astype(np.uint8))
...
...
@@ -612,7 +654,14 @@ class Normalize(BaseTransform):
'CHW'. Default: 'CHW'.
to_rgb (bool, optional): Whether to convert to rgb. Default: False.
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): A normalized array or tensor.
Returns:
A callable object of Normalize.
Examples:
.. code-block:: python
...
...
@@ -665,7 +714,15 @@ class Transpose(BaseTransform):
Args:
order (list|tuple, optional): Target order of input data. Default: (2, 0, 1).
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(np.ndarray|Paddle.Tensor): A transposed array or tensor. If input
is a PIL.Image, output will be converted to np.ndarray automatically.
Returns:
A callable object of Transpose.
Examples:
.. code-block:: python
...
...
@@ -707,6 +764,13 @@ class BrightnessTransform(BaseTransform):
non negative number. 0 gives the original image
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): An image with a transform in brghtness.
Returns:
A callable object of BrightnessTransform.
Examples:
.. code-block:: python
...
...
@@ -743,6 +807,13 @@ class ContrastTransform(BaseTransform):
non negative number. 0 gives the original image
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): An image with a transform in contrast.
Returns:
A callable object of ContrastTransform.
Examples:
.. code-block:: python
...
...
@@ -781,6 +852,13 @@ class SaturationTransform(BaseTransform):
non negative number. 0 gives the original image
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): An image with a transform in saturation.
Returns:
A callable object of SaturationTransform.
Examples:
.. code-block:: python
...
...
@@ -817,6 +895,13 @@ class HueTransform(BaseTransform):
between 0 and 0.5, 0 gives the original image
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): An image with a transform in hue.
Returns:
A callable object of HueTransform.
Examples:
.. code-block:: python
...
...
@@ -860,6 +945,13 @@ class ColorJitter(BaseTransform):
Chosen uniformly from [-hue, hue]. Should have 0<= hue <= 0.5.
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): A color jittered image.
Returns:
A callable object of ColorJitter.
Examples:
.. code-block:: python
...
...
@@ -938,7 +1030,14 @@ class RandomCrop(BaseTransform):
pad_if_needed (boolean|optional): It will pad the image if smaller than the
desired size to avoid raising an exception. Default: False.
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): A random cropped image.
Returns:
A callable object of RandomCrop.
Examples:
.. code-block:: python
...
...
@@ -1040,7 +1139,14 @@ class Pad(BaseTransform):
padding ``[1, 2, 3, 4]`` with 2 elements on both sides in symmetric mode
will result in ``[2, 1, 1, 2, 3, 4, 4, 3]``.
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): A paded image.
Returns:
A callable object of Pad.
Examples:
.. code-block:: python
...
...
@@ -1113,7 +1219,14 @@ class RandomRotation(BaseTransform):
Origin is the upper left corner.
Default is the center of the image.
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): A rotated image.
Returns:
A callable object of RandomRotation.
Examples:
.. code-block:: python
...
...
@@ -1180,11 +1293,15 @@ class Grayscale(BaseTransform):
Args:
num_output_channels (int): (1 or 3) number of channels desired for output image
keys (list[str]|tuple[str], optional): Same as ``BaseTransform``. Default: None.
Shape:
- img(PIL.Image|np.ndarray|Paddle.Tensor): The input image with shape (H x W x C).
- output(PIL.Image|np.ndarray|Paddle.Tensor): Grayscale version of the input image.
- If output_channels == 1 : returned image is single channel
- If output_channels == 3 : returned image is 3 channel with r == g == b
Returns:
CV Image: Grayscale version of the input.
- If output_channels == 1 : returned image is single channel
- If output_channels == 3 : returned image is 3 channel with r == g == b
A callable object of Grayscale.
Examples:
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录