From 80642bee00c3f723d213b0475749aeee60d89795 Mon Sep 17 00:00:00 2001 From: wanghaoshuang Date: Wed, 28 Jun 2017 08:22:58 +0800 Subject: [PATCH] fix_xmap and refine flowers dataset --- python/paddle/v2/dataset/__init__.py | 3 +- python/paddle/v2/dataset/flowers.py | 67 ++++++++++--------- .../paddle/v2/dataset/tests/flowers_test.py | 4 +- python/paddle/v2/reader/decorator.py | 47 +++++++------ .../paddle/v2/reader/tests/decorator_test.py | 18 ++--- 5 files changed, 72 insertions(+), 67 deletions(-) diff --git a/python/paddle/v2/dataset/__init__.py b/python/paddle/v2/dataset/__init__.py index 26252d5bbd..2e4beb6882 100644 --- a/python/paddle/v2/dataset/__init__.py +++ b/python/paddle/v2/dataset/__init__.py @@ -25,8 +25,9 @@ import uci_housing import sentiment import wmt14 import mq2007 +import flowers __all__ = [ 'mnist', 'imikolov', 'imdb', 'cifar', 'movielens', 'conll05', 'sentiment' - 'uci_housing', 'wmt14', 'mq2007' + 'uci_housing', 'wmt14', 'mq2007', 'flowers' ] diff --git a/python/paddle/v2/dataset/flowers.py b/python/paddle/v2/dataset/flowers.py index 07c13cf719..a181f3881a 100644 --- a/python/paddle/v2/dataset/flowers.py +++ b/python/paddle/v2/dataset/flowers.py @@ -13,18 +13,18 @@ # limitations under the License. """ This module will download dataset from -http://www.robots.ox.ac.uk/~vgg/data/flowers/102/index.html +http://www.robots.ox.ac.uk/~vgg/data/flowers/102/index.html and parse train/test set intopaddle reader creators. -This set contains images of flowers belonging to 102 different categories. +This set contains images of flowers belonging to 102 different categories. The images were acquired by searching the web and taking pictures. There are a minimum of 40 images for each category. The database was used in: Nilsback, M-E. and Zisserman, A. Automated flower classification over a large - number of classes.Proceedings of the Indian Conference on Computer Vision, -Graphics and Image Processing (2008) + number of classes.Proceedings of the Indian Conference on Computer Vision, +Graphics and Image Processing (2008) http://www.robots.ox.ac.uk/~vgg/publications/papers/nilsback08.{pdf,ps.gz}. """ @@ -34,9 +34,9 @@ from common import download import tarfile import scipy.io as scio from paddle.v2.image import * +from paddle.v2.reader import * import os import numpy as np -import paddle.v2 as paddle from multiprocessing import cpu_count __all__ = ['train', 'test', 'valid'] @@ -53,8 +53,8 @@ def default_mapper(sample): map image bytes data to type needed by model input layer ''' img, label = sample - img = paddle.image.load_image_bytes(img) - img = paddle.image.simple_transform(img, 256, 224, True) + img = load_image_bytes(img) + img = simple_transform(img, 256, 224, True) return img.flatten().astype('float32'), label @@ -63,22 +63,23 @@ def reader_creator(data_file, setid_file, dataset_name, mapper=default_mapper, - buffered_size=1024): + buffered_size=1024, + useXmap=True): ''' - 1. read images from tar file and + 1. read images from tar file and merge images into batch files in 102flowers.tgz_batch/ 2. get a reader to read sample from batch file - - :param data_file: downloaded data file + + :param data_file: downloaded data file :type data_file: string - :param label_file: downloaded label file + :param label_file: downloaded label file :type label_file: string :param setid_file: downloaded setid file containing information about how to split dataset :type setid_file: string :param dataset_name: data set name (tstid|trnid|valid) :type dataset_name: string - :param mapper: a function to map image bytes data to type + :param mapper: a function to map image bytes data to type needed by model input layer :type mapper: callable :param buffered_size: the size of buffer used to process images @@ -105,15 +106,17 @@ def reader_creator(data_file, for sample, label in itertools.izip(data, batch['label']): yield sample, int(label) - return paddle.reader.xmap_readers(mapper, reader, - cpu_count(), buffered_size) + if useXmap: + return xmap_readers(mapper, reader, cpu_count(), buffered_size) + else: + return map_readers(mapper, reader) -def train(mapper=default_mapper, buffered_size=1024): +def train(mapper=default_mapper, buffered_size=1024, useXmap=True): ''' - Create flowers training set reader. - It returns a reader, each sample in the reader is - image pixels in [0, 1] and label in [1, 102] + Create flowers training set reader. + It returns a reader, each sample in the reader is + image pixels in [0, 1] and label in [1, 102] translated from original color image by steps: 1. resize to 256*256 2. random crop to 224*224 @@ -128,15 +131,15 @@ def train(mapper=default_mapper, buffered_size=1024): return reader_creator( download(DATA_URL, 'flowers', DATA_MD5), download(LABEL_URL, 'flowers', LABEL_MD5), - download(SETID_URL, 'flowers', SETID_MD5), 'trnid', mapper, - buffered_size) + download(SETID_URL, 'flowers', SETID_MD5), 'tstid', mapper, + buffered_size, useXmap) -def test(mapper=default_mapper, buffered_size=1024): +def test(mapper=default_mapper, buffered_size=1024, useXmap=True): ''' - Create flowers test set reader. - It returns a reader, each sample in the reader is - image pixels in [0, 1] and label in [1, 102] + Create flowers test set reader. + It returns a reader, each sample in the reader is + image pixels in [0, 1] and label in [1, 102] translated from original color image by steps: 1. resize to 256*256 2. random crop to 224*224 @@ -151,15 +154,15 @@ def test(mapper=default_mapper, buffered_size=1024): return reader_creator( download(DATA_URL, 'flowers', DATA_MD5), download(LABEL_URL, 'flowers', LABEL_MD5), - download(SETID_URL, 'flowers', SETID_MD5), 'tstid', mapper, - buffered_size) + download(SETID_URL, 'flowers', SETID_MD5), 'trnid', mapper, + buffered_size, useXmap) -def valid(mapper=default_mapper, buffered_size=1024): +def valid(mapper=default_mapper, buffered_size=1024, useXmap=True): ''' - Create flowers validation set reader. - It returns a reader, each sample in the reader is - image pixels in [0, 1] and label in [1, 102] + Create flowers validation set reader. + It returns a reader, each sample in the reader is + image pixels in [0, 1] and label in [1, 102] translated from original color image by steps: 1. resize to 256*256 2. random crop to 224*224 @@ -175,7 +178,7 @@ def valid(mapper=default_mapper, buffered_size=1024): download(DATA_URL, 'flowers', DATA_MD5), download(LABEL_URL, 'flowers', LABEL_MD5), download(SETID_URL, 'flowers', SETID_MD5), 'valid', mapper, - buffered_size) + buffered_size, useXmap) def fetch(): diff --git a/python/paddle/v2/dataset/tests/flowers_test.py b/python/paddle/v2/dataset/tests/flowers_test.py index cc0626f4fe..a8ae9a07ac 100644 --- a/python/paddle/v2/dataset/tests/flowers_test.py +++ b/python/paddle/v2/dataset/tests/flowers_test.py @@ -31,13 +31,13 @@ class TestFlowers(unittest.TestCase): def test_train(self): instances, max_label_value = self.check_reader( paddle.v2.dataset.flowers.train()) - self.assertEqual(instances, 1020) + self.assertEqual(instances, 6149) self.assertEqual(max_label_value, 102) def test_test(self): instances, max_label_value = self.check_reader( paddle.v2.dataset.flowers.test()) - self.assertEqual(instances, 6149) + self.assertEqual(instances, 1020) self.assertEqual(max_label_value, 102) def test_valid(self): diff --git a/python/paddle/v2/reader/decorator.py b/python/paddle/v2/reader/decorator.py index e432003129..45a4288751 100644 --- a/python/paddle/v2/reader/decorator.py +++ b/python/paddle/v2/reader/decorator.py @@ -166,12 +166,12 @@ def buffered(reader, size): The buffered data reader will read and save data entries into a buffer. Reading from the buffered data reader will proceed as long as the buffer is not empty. - + :param reader: the data reader to read from. :type reader: callable :param size: max buffer size. :type size: int - + :returns: the buffered data reader. """ @@ -238,7 +238,7 @@ def xmap_readers(mapper, reader, process_num, buffer_size, order=False): :type mapper: callable :param reader: the data reader to read from :type reader: callable - :param process_num: process number to handle original sample + :param process_num: process number to handle original sample :type process_num: int :param buffer_size: max buffer size :type buffer_size: int @@ -248,9 +248,6 @@ def xmap_readers(mapper, reader, process_num, buffer_size, order=False): :rtype: callable """ end = XmapEndSignal() - in_queue = Queue(buffer_size) - out_queue = Queue(buffer_size) - out_order = [0] # define a worker to read samples from reader to in_queue def read_worker(reader, in_queue): @@ -266,12 +263,6 @@ def xmap_readers(mapper, reader, process_num, buffer_size, order=False): in_order += 1 in_queue.put(end) - # start a read worker in a thread - target = order_read_worker if order else read_worker - t = Thread(target=target, args=(reader, in_queue)) - t.daemon = True - t.start() - # define a worker to handle samples from in_queue by mapper # and put mapped samples into out_queue def handle_worker(in_queue, out_queue, mapper): @@ -298,19 +289,27 @@ def xmap_readers(mapper, reader, process_num, buffer_size, order=False): in_queue.put(end) out_queue.put(end) - # start several handle_workers - target = order_handle_worker if order else handle_worker - args = (in_queue, out_queue, mapper, out_order) if order else ( - in_queue, out_queue, mapper) - workers = [] - for i in xrange(process_num): - worker = Thread(target=target, args=args) - worker.daemon = True - workers.append(worker) - for w in workers: - w.start() - def xreader(): + in_queue = Queue(buffer_size) + out_queue = Queue(buffer_size) + out_order = [0] + # start a read worker in a thread + target = order_read_worker if order else read_worker + t = Thread(target=target, args=(reader, in_queue)) + t.daemon = True + t.start() + # start several handle_workers + target = order_handle_worker if order else handle_worker + args = (in_queue, out_queue, mapper, out_order) if order else ( + in_queue, out_queue, mapper) + workers = [] + for i in xrange(process_num): + worker = Thread(target=target, args=args) + worker.daemon = True + workers.append(worker) + for w in workers: + w.start() + sample = out_queue.get() while not isinstance(sample, XmapEndSignal): yield sample diff --git a/python/paddle/v2/reader/tests/decorator_test.py b/python/paddle/v2/reader/tests/decorator_test.py index bb3c5d220b..5a92951b10 100644 --- a/python/paddle/v2/reader/tests/decorator_test.py +++ b/python/paddle/v2/reader/tests/decorator_test.py @@ -132,15 +132,17 @@ class TestXmap(unittest.TestCase): for order in orders: for tNum in thread_nums: for size in buffered_size: - result = [] - for i in paddle.v2.reader.xmap_readers(mapper, + reader = paddle.v2.reader.xmap_readers(mapper, reader_creator_10(0), - tNum, size, order)(): - result.append(i) - if not order: - result.sort() - for idx, e in enumerate(result): - self.assertEqual(e, mapper(idx)) + tNum, size, order) + for n in xrange(3): + result = [] + for i in reader(): + result.append(i) + if not order: + result.sort() + for idx, e in enumerate(result): + self.assertEqual(e, mapper(idx)) if __name__ == '__main__': -- GitLab