From 151332298330b6eb1a42ec31a4d977a8611072c9 Mon Sep 17 00:00:00 2001 From: Luo Tao Date: Wed, 8 Nov 2017 17:04:46 +0800 Subject: [PATCH] add doc for image.py --- doc/api/v2/data.rst | 113 ++------------------------------ doc/api/v2/data/data_reader.rst | 36 ++++++++++ doc/api/v2/data/dataset.rst | 75 +++++++++++++++++++++ doc/api/v2/data/image.rst | 5 ++ python/paddle/v2/image.py | 74 ++++++++++++++------- 5 files changed, 170 insertions(+), 133 deletions(-) create mode 100644 doc/api/v2/data/data_reader.rst create mode 100644 doc/api/v2/data/dataset.rst create mode 100644 doc/api/v2/data/image.rst diff --git a/doc/api/v2/data.rst b/doc/api/v2/data.rst index fef87c4fbd..b56c7332cc 100644 --- a/doc/api/v2/data.rst +++ b/doc/api/v2/data.rst @@ -2,112 +2,9 @@ Data Reader Interface and DataSets ================================== +.. toctree:: + :maxdepth: 1 -DataTypes -========= - -.. automodule:: paddle.v2.data_type - :members: - :noindex: - -DataFeeder -========== - -.. automodule:: paddle.v2.data_feeder - :members: - :noindex: - -Reader -====== - -.. automodule:: paddle.v2.reader - :members: - :noindex: - -.. automodule:: paddle.v2.reader.creator - :members: - :noindex: - -minibatch -========= - -.. automodule:: paddle.v2.minibatch - :members: - :noindex: - -Dataset -======= - -.. automodule:: paddle.v2.dataset - :members: - :noindex: - -mnist -+++++ - -.. automodule:: paddle.v2.dataset.mnist - :members: - :noindex: - -cifar -+++++ - -.. automodule:: paddle.v2.dataset.cifar - :members: - :noindex: - -conll05 -+++++++ - -.. automodule:: paddle.v2.dataset.conll05 - :members: get_dict,get_embedding,test - :noindex: - -imdb -++++ - -.. automodule:: paddle.v2.dataset.imdb - :members: - :noindex: - -imikolov -++++++++ - -.. automodule:: paddle.v2.dataset.imikolov - :members: - :noindex: - -movielens -+++++++++ - -.. automodule:: paddle.v2.dataset.movielens - :members: - :noindex: - -.. autoclass:: paddle.v2.dataset.movielens.MovieInfo - :noindex: - -.. autoclass:: paddle.v2.dataset.movielens.UserInfo - :noindex: - -sentiment -+++++++++ - -.. automodule:: paddle.v2.dataset.sentiment - :members: - :noindex: - -uci_housing -+++++++++++ - -.. automodule:: paddle.v2.dataset.uci_housing - :members: - :noindex: - -wmt14 -+++++ - -.. automodule:: paddle.v2.dataset.wmt14 - :members: - :noindex: - + data/data_reader.rst + data/image.rst + data/dataset.rst diff --git a/doc/api/v2/data/data_reader.rst b/doc/api/v2/data/data_reader.rst new file mode 100644 index 0000000000..2ccfec9c28 --- /dev/null +++ b/doc/api/v2/data/data_reader.rst @@ -0,0 +1,36 @@ +===================== +Data Reader Interface +===================== + + +DataTypes +========= + +.. automodule:: paddle.v2.data_type + :members: + :noindex: + +DataFeeder +========== + +.. automodule:: paddle.v2.data_feeder + :members: + :noindex: + +Reader +====== + +.. automodule:: paddle.v2.reader + :members: + :noindex: + +.. automodule:: paddle.v2.reader.creator + :members: + :noindex: + +minibatch +========= + +.. automodule:: paddle.v2.minibatch + :members: + :noindex: diff --git a/doc/api/v2/data/dataset.rst b/doc/api/v2/data/dataset.rst new file mode 100644 index 0000000000..6a8ecc5bb1 --- /dev/null +++ b/doc/api/v2/data/dataset.rst @@ -0,0 +1,75 @@ +Dataset +======= + +.. automodule:: paddle.v2.dataset + :members: + :noindex: + +mnist ++++++ + +.. automodule:: paddle.v2.dataset.mnist + :members: + :noindex: + +cifar ++++++ + +.. automodule:: paddle.v2.dataset.cifar + :members: + :noindex: + +conll05 ++++++++ + +.. automodule:: paddle.v2.dataset.conll05 + :members: get_dict,get_embedding,test + :noindex: + +imdb +++++ + +.. automodule:: paddle.v2.dataset.imdb + :members: + :noindex: + +imikolov +++++++++ + +.. automodule:: paddle.v2.dataset.imikolov + :members: + :noindex: + +movielens ++++++++++ + +.. automodule:: paddle.v2.dataset.movielens + :members: + :noindex: + +.. autoclass:: paddle.v2.dataset.movielens.MovieInfo + :noindex: + +.. autoclass:: paddle.v2.dataset.movielens.UserInfo + :noindex: + +sentiment ++++++++++ + +.. automodule:: paddle.v2.dataset.sentiment + :members: + :noindex: + +uci_housing ++++++++++++ + +.. automodule:: paddle.v2.dataset.uci_housing + :members: + :noindex: + +wmt14 ++++++ + +.. automodule:: paddle.v2.dataset.wmt14 + :members: + :noindex: diff --git a/doc/api/v2/data/image.rst b/doc/api/v2/data/image.rst new file mode 100644 index 0000000000..97651ffa6b --- /dev/null +++ b/doc/api/v2/data/image.rst @@ -0,0 +1,5 @@ +Image Interface +=============== + +.. automodule:: paddle.v2.image + :members: diff --git a/python/paddle/v2/image.py b/python/paddle/v2/image.py index 965d965335..7408ea8ef6 100644 --- a/python/paddle/v2/image.py +++ b/python/paddle/v2/image.py @@ -1,33 +1,35 @@ -import numpy as np -try: - import cv2 -except ImportError: - cv2 = None -import os -import tarfile -import cPickle - -__all__ = [ - "load_image_bytes", "load_image", "resize_short", "to_chw", "center_crop", - "random_crop", "left_right_flip", "simple_transform", "load_and_transform", - "batch_images_from_tar" -] """ This file contains some common interfaces for image preprocess. Many users are confused about the image layout. We introduce the image layout as follows. - CHW Layout + - The abbreviations: C=channel, H=Height, W=Width - The default layout of image opened by cv2 or PIL is HWC. PaddlePaddle only supports the CHW layout. And CHW is simply a transpose of HWC. It must transpose the input image. - Color format: RGB or BGR + OpenCV use BGR color format. PIL use RGB color format. Both formats can be used for training. Noted that, the format should be keep consistent between the training and inference peroid. """ +import numpy as np +try: + import cv2 +except ImportError: + cv2 = None +import os +import tarfile +import cPickle + +__all__ = [ + "load_image_bytes", "load_image", "resize_short", "to_chw", "center_crop", + "random_crop", "left_right_flip", "simple_transform", "load_and_transform", + "batch_images_from_tar" +] def batch_images_from_tar(data_file, @@ -36,17 +38,18 @@ def batch_images_from_tar(data_file, num_per_batch=1024): """ Read images from tar file and batch them into batch file. - param data_file: path of image tar file - type data_file: string - param dataset_name: 'train','test' or 'valid' - type dataset_name: string - param img2label: a dic with image file name as key + + :param data_file: path of image tar file + :type data_file: string + :param dataset_name: 'train','test' or 'valid' + :type dataset_name: string + :param img2label: a dic with image file name as key and image's label as value - type img2label: dic - param num_per_batch: image number per batch file - type num_per_batch: int - return: path of list file containing paths of batch file - rtype: string + :type img2label: dic + :param num_per_batch: image number per batch file + :type num_per_batch: int + :return: path of list file containing paths of batch file + :rtype: string """ batch_dir = data_file + "_batch" out_path = "%s/%s" % (batch_dir, dataset_name) @@ -99,14 +102,16 @@ def load_image_bytes(bytes, is_color=True): Example usage: .. code-block:: python + with open('cat.jpg') as f: im = load_image_bytes(f.read()) :param bytes: the input image bytes array. - :type file: str + :type bytes: str :param is_color: If set is_color True, it will load and return a color image. Otherwise, it will load and return a gray image. + :type is_color: bool """ flag = 1 if is_color else 0 file_bytes = np.asarray(bytearray(bytes), dtype=np.uint8) @@ -121,6 +126,7 @@ def load_image(file, is_color=True): Example usage: .. code-block:: python + im = load_image('cat.jpg') :param file: the input image path. @@ -128,6 +134,7 @@ def load_image(file, is_color=True): :param is_color: If set is_color True, it will load and return a color image. Otherwise, it will load and return a gray image. + :type is_color: bool """ # cv2.IMAGE_COLOR for OpenCV3 # cv2.CV_LOAD_IMAGE_COLOR for older OpenCV Version @@ -147,6 +154,7 @@ def resize_short(im, size): Example usage: .. code-block:: python + im = load_image('cat.jpg') im = resize_short(im, 256) @@ -175,6 +183,7 @@ def to_chw(im, order=(2, 0, 1)): Example usage: .. code-block:: python + im = load_image('cat.jpg') im = resize_short(im, 256) im = to_chw(im) @@ -196,6 +205,7 @@ def center_crop(im, size, is_color=True): Example usage: .. code-block:: python + im = center_crop(im, 224) :param im: the input image with HWC layout. @@ -223,6 +233,7 @@ def random_crop(im, size, is_color=True): Example usage: .. code-block:: python + im = random_crop(im, 224) :param im: the input image with HWC layout. @@ -251,6 +262,7 @@ def left_right_flip(im): Example usage: .. code-block:: python + im = left_right_flip(im) :paam im: input image with HWC layout @@ -275,6 +287,7 @@ def simple_transform(im, Example usage: .. code-block:: python + im = simple_transform(im, 256, 224, True) :param im: The input image with HWC layout. @@ -285,6 +298,11 @@ def simple_transform(im, :type crop_size: int :param is_train: Whether it is training or not. :type is_train: bool + :param is_color: whether the image is color or not. + :type is_color: bool + :param mean: the mean values, which can be element-wise mean values or + mean values per channel. + :type mean: numpy array | list """ im = resize_short(im, resize_size) if is_train: @@ -324,6 +342,7 @@ def load_and_transform(filename, Example usage: .. code-block:: python + im = load_and_transform('cat.jpg', 256, 224, True) :param filename: The file name of input image. @@ -334,6 +353,11 @@ def load_and_transform(filename, :type crop_size: int :param is_train: Whether it is training or not. :type is_train: bool + :param is_color: whether the image is color or not. + :type is_color: bool + :param mean: the mean values, which can be element-wise mean values or + mean values per channel. + :type mean: numpy array | list """ im = load_image(filename) im = simple_transform(im, resize_size, crop_size, is_train, is_color, mean) -- GitLab