Merge branch 'feature/clean_mnist_v2' into feature/tester

Author: reyoung

.travis.yml

@@ -57,7 +57,7 @@ before_install:
   - if [[ "$JOB" == "PRE_COMMIT" ]]; then sudo ln -s /usr/bin/clang-format-3.8 /usr/bin/clang-format; fi
   # Paddle is using protobuf 3.1 currently. Protobuf 3.2 breaks the compatibility. So we specify the python 
   # protobuf version.
-  - pip install numpy wheel 'protobuf==3.1' sphinx recommonmark sphinx_rtd_theme virtualenv pre-commit requests==2.9.2 LinkChecker 'scikit-learn>=0.18.0' 'scipy>=0.18.0'
+  - pip install numpy wheel 'protobuf==3.1' sphinx recommonmark sphinx_rtd_theme virtualenv pre-commit requests==2.9.2 LinkChecker
 script:
   - paddle/scripts/travis/main.sh
 notifications:

demo/mnist/api_train_v2.py

@@ -1,4 +1,3 @@
-import numpy
 import paddle.v2 as paddle
 
 
@@ -41,7 +40,7 @@ def event_handler(event):
     trainer.train(
         reader=paddle.reader.batched(
             paddle.reader.shuffle(
-                paddle.dataset.mnist.train_creator(), buf_size=8192),
+                paddle.dataset.mnist.train(), buf_size=8192),
             batch_size=32),
         event_handler=event_handler)
 

python/paddle/v2/__init__.py

@@ -18,6 +18,7 @@
 import trainer
 import event
 import data_type
+import topology
 import data_feeder
 from . import dataset
 from . import reader
@@ -27,7 +28,8 @@
 
 __all__ = [
     'optimizer', 'layer', 'activation', 'parameters', 'init', 'trainer',
-    'event', 'data_type', 'attr', 'pooling', 'data_feeder', 'dataset', 'reader'
+    'event', 'data_type', 'attr', 'pooling', 'data_feeder', 'dataset', 'reader',
+    'topology'
 ]
 
 

python/paddle/v2/data_feeder.py

@@ -23,7 +23,7 @@ class DataFeeder(DataProviderConverter):
     """
     DataFeeder converts the data returned by paddle.reader into a data structure
     of Arguments which is defined in the API. The paddle.reader usually returns
-    a list of mini-batch data entries. Each data entry in the list is one sampe.
+    a list of mini-batch data entries. Each data entry in the list is one sample.
     Each sample is a list or a tuple with one feature or multiple features.
     DataFeeder converts this mini-batch data entries into Arguments in order
     to feed it to C++ interface.

python/paddle/v2/data_type.py

@@ -13,10 +13,10 @@
 # limitations under the License.
 
 from paddle.trainer.PyDataProvider2 import \
-    InputType, dense_vector, sparse_binary_vector,\
+    InputType, DataType, dense_vector, sparse_binary_vector,\
     sparse_vector, integer_value, integer_value_sequence
 
 __all__ = [
-    'InputType', 'dense_vector', 'sparse_binary_vector', 'sparse_vector',
-    'integer_value', 'integer_value_sequence'
+    'InputType', 'DataType', 'dense_vector', 'sparse_binary_vector',
+    'sparse_vector', 'integer_value', 'integer_value_sequence'
 ]

python/paddle/v2/dataset/cifar.py

@@ -1,82 +1,61 @@
 """
-CIFAR Dataset.
-
-URL: https://www.cs.toronto.edu/~kriz/cifar.html
-
-the default train_creator, test_creator used for CIFAR-10 dataset.
+CIFAR dataset: https://www.cs.toronto.edu/~kriz/cifar.html
 """
 import cPickle
 import itertools
-import tarfile
-
 import numpy
+import paddle.v2.dataset.common
+import tarfile
 
-from common import download
-
-__all__ = [
-    'cifar_100_train_creator', 'cifar_100_test_creator', 'train_creator',
-    'test_creator'
-]
+__all__ = ['train100', 'test100', 'train10', 'test10']
 
-CIFAR10_URL = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
+URL_PREFIX = 'https://www.cs.toronto.edu/~kriz/'
+CIFAR10_URL = URL_PREFIX + 'cifar-10-python.tar.gz'
 CIFAR10_MD5 = 'c58f30108f718f92721af3b95e74349a'
-CIFAR100_URL = 'https://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz'
+CIFAR100_URL = URL_PREFIX + 'cifar-100-python.tar.gz'
 CIFAR100_MD5 = 'eb9058c3a382ffc7106e4002c42a8d85'
 
 
-def __read_batch__(filename, sub_name):
-    def reader():
-        def __read_one_batch_impl__(batch):
-            data = batch['data']
-            labels = batch.get('labels', batch.get('fine_labels', None))
-            assert labels is not None
-            for sample, label in itertools.izip(data, labels):
-                yield (sample / 255.0).astype(numpy.float32), int(label)
+def reader_creator(filename, sub_name):
+    def read_batch(batch):
+        data = batch['data']
+        labels = batch.get('labels', batch.get('fine_labels', None))
+        assert labels is not None
+        for sample, label in itertools.izip(data, labels):
+            yield (sample / 255.0).astype(numpy.float32), int(label)
 
+    def reader():
         with tarfile.open(filename, mode='r') as f:
             names = (each_item.name for each_item in f
                      if sub_name in each_item.name)
 
             for name in names:
                 batch = cPickle.load(f.extractfile(name))
-                for item in __read_one_batch_impl__(batch):
+                for item in read_batch(batch):
                     yield item
 
     return reader
 
 
-def cifar_100_train_creator():
-    fn = download(url=CIFAR100_URL, md5=CIFAR100_MD5)
-    return __read_batch__(fn, 'train')
-
-
-def cifar_100_test_creator():
-    fn = download(url=CIFAR100_URL, md5=CIFAR100_MD5)
-    return __read_batch__(fn, 'test')
-
-
-def train_creator():
-    """
-    Default train reader creator. Use CIFAR-10 dataset.
-    """
-    fn = download(url=CIFAR10_URL, md5=CIFAR10_MD5)
-    return __read_batch__(fn, 'data_batch')
+def train100():
+    return reader_creator(
+        paddle.v2.dataset.common.download(CIFAR100_URL, 'cifar', CIFAR100_MD5),
+        'train')
 
 
-def test_creator():
-    """
-    Default test reader creator. Use CIFAR-10 dataset.
-    """
-    fn = download(url=CIFAR10_URL, md5=CIFAR10_MD5)
-    return __read_batch__(fn, 'test_batch')
+def test100():
+    return reader_creator(
+        paddle.v2.dataset.common.download(CIFAR100_URL, 'cifar', CIFAR100_MD5),
+        'test')
 
 
-def unittest():
-    for _ in train_creator()():
-        pass
-    for _ in test_creator()():
-        pass
+def train10():
+    return reader_creator(
+        paddle.v2.dataset.common.download(CIFAR10_URL, 'cifar', CIFAR10_MD5),
+        'data_batch')
 
 
-if __name__ == '__main__':
-    unittest()
+def test10():
+    return reader_creator(
+        paddle.v2.dataset.common.download(CIFAR10_URL, 'cifar', CIFAR10_MD5),
+        'test_batch')

python/paddle/v2/dataset/common.py

@@ -27,7 +27,6 @@ def download(url, module_name, md5sum):
 
     filename = os.path.join(dirname, url.split('/')[-1])
     if not (os.path.exists(filename) and md5file(filename) == md5sum):
-        # If file doesn't exist or MD5 doesn't match, then download.
         r = requests.get(url, stream=True)
         with open(filename, 'w') as f:
             shutil.copyfileobj(r.raw, f)

python/paddle/v2/dataset/mnist.py

@@ -1,11 +1,13 @@
+"""
+MNIST dataset.
+"""
 import paddle.v2.dataset.common
 import subprocess
 import numpy
-
+import platform
 __all__ = ['train', 'test']
 
 URL_PREFIX = 'http://yann.lecun.com/exdb/mnist/'
-
 TEST_IMAGE_URL = URL_PREFIX + 't10k-images-idx3-ubyte.gz'
 TEST_IMAGE_MD5 = '25e3cc63507ef6e98d5dc541e8672bb6'
 TEST_LABEL_URL = URL_PREFIX + 't10k-labels-idx1-ubyte.gz'
@@ -18,12 +20,19 @@
 
 def reader_creator(image_filename, label_filename, buffer_size):
     def reader():
+        if platform.system() == 'Darwin':
+            zcat_cmd = 'gzcat'
+        elif platform.system() == 'Linux':
+            zcat_cmd = 'zcat'
+        else:
+            raise NotImplementedError()
+
         # According to http://stackoverflow.com/a/38061619/724872, we
         # cannot use standard package gzip here.
-        m = subprocess.Popen(["zcat", image_filename], stdout=subprocess.PIPE)
+        m = subprocess.Popen([zcat_cmd, image_filename], stdout=subprocess.PIPE)
         m.stdout.read(16)  # skip some magic bytes
 
-        l = subprocess.Popen(["zcat", label_filename], stdout=subprocess.PIPE)
+        l = subprocess.Popen([zcat_cmd, label_filename], stdout=subprocess.PIPE)
         l.stdout.read(8)  # skip some magic bytes
 
         while True:
@@ -40,12 +49,12 @@ def reader():
             images = images / 255.0 * 2.0 - 1.0
 
             for i in xrange(buffer_size):
-                yield images[i, :], labels[i]
+                yield images[i, :], int(labels[i])
 
         m.terminate()
         l.terminate()
 
-    return reader()
+    return reader
 
 
 def train():

python/paddle/v2/dataset/tests/cifar_test.py

@@ -0,0 +1,42 @@
+import paddle.v2.dataset.cifar
+import unittest
+
+
+class TestCIFAR(unittest.TestCase):
+    def check_reader(self, reader):
+        sum = 0
+        label = 0
+        for l in reader():
+            self.assertEqual(l[0].size, 3072)
+            if l[1] > label:
+                label = l[1]
+            sum += 1
+        return sum, label
+
+    def test_test10(self):
+        instances, max_label_value = self.check_reader(
+            paddle.v2.dataset.cifar.test10())
+        self.assertEqual(instances, 10000)
+        self.assertEqual(max_label_value, 9)
+
+    def test_train10(self):
+        instances, max_label_value = self.check_reader(
+            paddle.v2.dataset.cifar.train10())
+        self.assertEqual(instances, 50000)
+        self.assertEqual(max_label_value, 9)
+
+    def test_test100(self):
+        instances, max_label_value = self.check_reader(
+            paddle.v2.dataset.cifar.test100())
+        self.assertEqual(instances, 10000)
+        self.assertEqual(max_label_value, 99)
+
+    def test_train100(self):
+        instances, max_label_value = self.check_reader(
+            paddle.v2.dataset.cifar.train100())
+        self.assertEqual(instances, 50000)
+        self.assertEqual(max_label_value, 99)
+
+
+if __name__ == '__main__':
+    unittest.main()

python/paddle/v2/dataset/tests/mnist_test.py

@@ -5,21 +5,25 @@
 class TestMNIST(unittest.TestCase):
     def check_reader(self, reader):
         sum = 0
-        for l in reader:
+        label = 0
+        for l in reader():
             self.assertEqual(l[0].size, 784)
-            self.assertEqual(l[1].size, 1)
-            self.assertLess(l[1], 10)
-            self.assertGreaterEqual(l[1], 0)
+            if l[1] > label:
+                label = l[1]
             sum += 1
-        return sum
+        return sum, label
 
     def test_train(self):
-        self.assertEqual(
-            self.check_reader(paddle.v2.dataset.mnist.train()), 60000)
+        instances, max_label_value = self.check_reader(
+            paddle.v2.dataset.mnist.train())
+        self.assertEqual(instances, 60000)
+        self.assertEqual(max_label_value, 9)
 
     def test_test(self):
-        self.assertEqual(
-            self.check_reader(paddle.v2.dataset.mnist.test()), 10000)
+        instances, max_label_value = self.check_reader(
+            paddle.v2.dataset.mnist.test())
+        self.assertEqual(instances, 10000)
+        self.assertEqual(max_label_value, 9)
 
 
 if __name__ == '__main__':