You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2018/03/23 21:09:00 UTC
[GitHub] piiswrong closed pull request #10155: [MXNet-111] Doc for gluon.data.transforms
piiswrong closed pull request #10155: [MXNet-111] Doc for gluon.data.transforms
URL: https://github.com/apache/incubator-mxnet/pull/10155
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git a/docs/api/python/gluon/data.md b/docs/api/python/gluon/data.md
index 28433c0ae36..3c6bb02e47c 100644
--- a/docs/api/python/gluon/data.md
+++ b/docs/api/python/gluon/data.md
@@ -69,6 +69,51 @@ In the rest of this document, we list routines provided by the `gluon.data` pack
ImageFolderDataset
```
+#### Vision Transforms
+
+```eval_rst
+.. currentmodule:: mxnet.gluon.data.vision.transforms
+```
+
+Transforms can be used to augment input data during training. You
+can compose multiple transforms sequentially, for example:
+
+```python
+from mxnet.gluon.data.vision import MNIST, transforms
+from mxnet import gluon
+transform = transforms.Compose([
+ transforms.Resize(300),
+ transforms.RandomResizedCrop(224),
+ transforms.RandomBrightness(0.1),
+ transforms.ToTensor(),
+ transforms.Normalize(0, 1)])
+data = MNIST(train=True).transform_first(transform)
+data_loader = gluon.data.DataLoader(data, batch_size=32, num_workers=1)
+for data, label in data_loader:
+ # do something with data and label
+```
+
+```eval_rst
+.. autosummary::
+ :nosignatures:
+
+ Compose
+ Cast
+ ToTensor
+ Normalize
+ RandomResizedCrop
+ CenterCrop
+ Resize
+ RandomFlipLeftRight
+ RandomFlipTopBottom
+ RandomBrightness
+ RandomContrast
+ RandomSaturation
+ RandomHue
+ RandomColorJitter
+ RandomLighting
+```
+
## API Reference
<script type="text/javascript" src='../../../_static/js/auto_module_index.js'></script>
@@ -84,6 +129,9 @@ In the rest of this document, we list routines provided by the `gluon.data` pack
.. automodule:: mxnet.gluon.data.vision.datasets
:members:
+
+.. automodule:: mxnet.gluon.data.vision.transforms
+ :members:
```
diff --git a/python/mxnet/gluon/data/vision/transforms.py b/python/mxnet/gluon/data/vision/transforms.py
index 8a87f374e46..a0734676a8d 100644
--- a/python/mxnet/gluon/data/vision/transforms.py
+++ b/python/mxnet/gluon/data/vision/transforms.py
@@ -32,6 +32,22 @@ class Compose(Sequential):
----------
transforms : list of transform Blocks.
The list of transforms to be composed.
+
+
+ Inputs:
+ - **data**: input tensor with shape of the first transform Block requires.
+
+ Outputs:
+ - **out**: output tensor with shape of the last transform Block produces.
+
+ Examples
+ --------
+ >>> transformer = transforms.Compose([transforms.Resize(300),
+ ... transforms.CenterCrop(256),
+ ... transforms.ToTensor()])
+ >>> image = mx.nd.random.uniform(0, 255, (224, 224, 3)).astype(dtype=np.uint8)
+ >>> transformer(image)
+ <NDArray 3x256x256 @cpu(0)>
"""
def __init__(self, transforms):
super(Compose, self).__init__()
@@ -60,6 +76,13 @@ class Cast(HybridBlock):
----------
dtype : str, default 'float32'
The target data type, in string or `numpy.dtype`.
+
+
+ Inputs:
+ - **data**: input tensor with arbitrary shape.
+
+ Outputs:
+ - **out**: output tensor with the same shape as `data`.
"""
def __init__(self, dtype='float32'):
super(Cast, self).__init__()
@@ -75,6 +98,31 @@ class ToTensor(HybridBlock):
Converts an image NDArray of shape (H x W x C) in the range
[0, 255] to a float32 tensor NDArray of shape (C x H x W) in
the range [0, 1).
+
+ Inputs:
+ - **data**: input tensor with (H x W x C) shape and uint8 type.
+
+ Outputs:
+ - **out**: output tensor with (C x H x W) shape and float32 type.
+
+ Examples
+ --------
+ >>> transformer = vision.transforms.ToTensor()
+ >>> image = mx.nd.random.uniform(0, 255, (4, 2, 3)).astype(dtype=np.uint8)
+ >>> transformer(image)
+ [[[ 0.85490197 0.72156864]
+ [ 0.09019608 0.74117649]
+ [ 0.61960787 0.92941177]
+ [ 0.96470588 0.1882353 ]]
+ [[ 0.6156863 0.73725492]
+ [ 0.46666667 0.98039216]
+ [ 0.44705883 0.45490196]
+ [ 0.01960784 0.8509804 ]]
+ [[ 0.39607844 0.03137255]
+ [ 0.72156864 0.52941179]
+ [ 0.16470589 0.7647059 ]
+ [ 0.05490196 0.70588237]]]
+ <NDArray 3x4x2 @cpu(0)>
"""
def __init__(self):
super(ToTensor, self).__init__()
@@ -100,6 +148,13 @@ class Normalize(HybridBlock):
The mean values.
std : float or tuple of floats
The standard deviation values.
+
+
+ Inputs:
+ - **data**: input tensor with (C x H x W) shape.
+
+ Outputs:
+ - **out**: output tensor with the shape as `data`.
"""
def __init__(self, mean, std):
super(Normalize, self).__init__()
@@ -129,6 +184,13 @@ class RandomResizedCrop(Block):
interpolation : int
Interpolation method for resizing. By default uses bilinear
interpolation. See OpenCV's resize function for available choices.
+
+
+ Inputs:
+ - **data**: input tensor with (Hi x Wi x C) shape.
+
+ Outputs:
+ - **out**: output tensor with (H x W x C) shape.
"""
def __init__(self, size, scale=(0.08, 1.0), ratio=(3.0/4.0, 4.0/3.0),
interpolation=2):
@@ -153,6 +215,20 @@ class CenterCrop(Block):
interpolation : int
Interpolation method for resizing. By default uses bilinear
interpolation. See OpenCV's resize function for available choices.
+
+
+ Inputs:
+ - **data**: input tensor with (Hi x Wi x C) shape.
+
+ Outputs:
+ - **out**: output tensor with (H x W x C) shape.
+
+ Examples
+ --------
+ >>> transformer = vision.transforms.CenterCrop(size=(1000, 500))
+ >>> image = mx.nd.random.uniform(0, 255, (2321, 3482, 3)).astype(dtype=np.uint8)
+ >>> transformer(image)
+ <NDArray 500x1000x3 @cpu(0)>
"""
def __init__(self, size, interpolation=2):
super(CenterCrop, self).__init__()
@@ -174,6 +250,20 @@ class Resize(Block):
interpolation : int
Interpolation method for resizing. By default uses bilinear
interpolation. See OpenCV's resize function for available choices.
+
+
+ Inputs:
+ - **data**: input tensor with (Hi x Wi x C) shape.
+
+ Outputs:
+ - **out**: output tensor with (H x W x C) shape.
+
+ Examples
+ --------
+ >>> transformer = vision.transforms.Resize(size=(1000, 500))
+ >>> image = mx.nd.random.uniform(0, 255, (224, 224, 3)).astype(dtype=np.uint8)
+ >>> transformer(image)
+ <NDArray 500x1000x3 @cpu(0)>
"""
def __init__(self, size, interpolation=2):
super(Resize, self).__init__()
@@ -188,6 +278,12 @@ def forward(self, x):
class RandomFlipLeftRight(HybridBlock):
"""Randomly flip the input image left to right with a probability
of 0.5.
+
+ Inputs:
+ - **data**: input tensor with (H x W x C) shape.
+
+ Outputs:
+ - **out**: output tensor with same shape as `data`.
"""
def __init__(self):
super(RandomFlipLeftRight, self).__init__()
@@ -199,6 +295,12 @@ def hybrid_forward(self, F, x):
class RandomFlipTopBottom(HybridBlock):
"""Randomly flip the input image top to bottom with a probability
of 0.5.
+
+ Inputs:
+ - **data**: input tensor with (H x W x C) shape.
+
+ Outputs:
+ - **out**: output tensor with same shape as `data`.
"""
def __init__(self):
super(RandomFlipTopBottom, self).__init__()
@@ -210,6 +312,19 @@ def hybrid_forward(self, F, x):
class RandomBrightness(HybridBlock):
"""Randomly jitters image brightness with a factor
chosen from `[max(0, 1 - brightness), 1 + brightness]`.
+
+ Parameters
+ ----------
+ brightness: float
+ How much to jitter brightness. brightness factor is randomly
+ chosen from `[max(0, 1 - brightness), 1 + brightness]`.
+
+
+ Inputs:
+ - **data**: input tensor with (H x W x C) shape.
+
+ Outputs:
+ - **out**: output tensor with same shape as `data`.
"""
def __init__(self, brightness):
super(RandomBrightness, self).__init__()
@@ -222,6 +337,19 @@ def hybrid_forward(self, F, x):
class RandomContrast(HybridBlock):
"""Randomly jitters image contrast with a factor
chosen from `[max(0, 1 - contrast), 1 + contrast]`.
+
+ Parameters
+ ----------
+ contrast: float
+ How much to jitter contrast. contrast factor is randomly
+ chosen from `[max(0, 1 - contrast), 1 + contrast]`.
+
+
+ Inputs:
+ - **data**: input tensor with (H x W x C) shape.
+
+ Outputs:
+ - **out**: output tensor with same shape as `data`.
"""
def __init__(self, contrast):
super(RandomContrast, self).__init__()
@@ -234,6 +362,19 @@ def hybrid_forward(self, F, x):
class RandomSaturation(HybridBlock):
"""Randomly jitters image saturation with a factor
chosen from `[max(0, 1 - saturation), 1 + saturation]`.
+
+ Parameters
+ ----------
+ saturation: float
+ How much to jitter saturation. saturation factor is randomly
+ chosen from `[max(0, 1 - saturation), 1 + saturation]`.
+
+
+ Inputs:
+ - **data**: input tensor with (H x W x C) shape.
+
+ Outputs:
+ - **out**: output tensor with same shape as `data`.
"""
def __init__(self, saturation):
super(RandomSaturation, self).__init__()
@@ -246,6 +387,19 @@ def hybrid_forward(self, F, x):
class RandomHue(HybridBlock):
"""Randomly jitters image hue with a factor
chosen from `[max(0, 1 - hue), 1 + hue]`.
+
+ Parameters
+ ----------
+ hue: float
+ How much to jitter hue. hue factor is randomly
+ chosen from `[max(0, 1 - hue), 1 + hue]`.
+
+
+ Inputs:
+ - **data**: input tensor with (H x W x C) shape.
+
+ Outputs:
+ - **out**: output tensor with same shape as `data`.
"""
def __init__(self, hue):
super(RandomHue, self).__init__()
@@ -273,6 +427,13 @@ class RandomColorJitter(HybridBlock):
hue : float
How much to jitter hue. hue factor is randomly
chosen from `[max(0, 1 - hue), 1 + hue]`.
+
+
+ Inputs:
+ - **data**: input tensor with (H x W x C) shape.
+
+ Outputs:
+ - **out**: output tensor with same shape as `data`.
"""
def __init__(self, brightness=0, contrast=0, saturation=0, hue=0):
super(RandomColorJitter, self).__init__()
@@ -289,6 +450,13 @@ class RandomLighting(HybridBlock):
----------
alpha : float
Intensity of the image.
+
+
+ Inputs:
+ - **data**: input tensor with (H x W x C) shape.
+
+ Outputs:
+ - **out**: output tensor with same shape as `data`.
"""
def __init__(self, alpha):
super(RandomLighting, self).__init__()
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services