More small revisions based on CR.

Examples/Image/Classification/ConvNet/Python/ConvNet_CIFAR10.py

@@ -24,13 +24,12 @@ model_path = os.path.join(abs_path, "Models")
 # Define the reader for both training and evaluation action.
 def create_reader(path, is_training, input_dim, label_dim):
     return MinibatchSource(CTFDeserializer(path, StreamDefs(
-        features  = StreamDef(field='features', shape=input_dim, is_sparse=False),
-        labels    = StreamDef(field='labels',   shape=label_dim, is_sparse=False)
+        features  = StreamDef(field='features', shape=input_dim),
+        labels    = StreamDef(field='labels',   shape=label_dim)
     )), randomize=is_training, epoch_size = INFINITELY_REPEAT if is_training else FULL_DATA_SWEEP)
 
 
 # Creates and trains a feedforward classification model for MNIST images
-
 def convnet_cifar10(debug_output=False):
     set_computation_network_trace_level(0)
 
@@ -56,7 +55,7 @@ def convnet_cifar10(debug_output=False):
             ]), 
             LayerStack(2, lambda i: [
                 Dense([256,128][i]), 
-                Dropout(0.5)            # dropout scheduling is not supported in Python yet 
+                Dropout(0.5)
             ]), 
             Dense(num_output_classes, activation=None)
         ])(scaled_input)

Examples/Image/Classification/ConvNet/Python/ConvNet_CIFAR10_DataAug.py

@@ -69,7 +69,7 @@ def convnet_cifar10_dataaug(reader_train, reader_test):
             ]), 
             LayerStack(2, lambda i: [
                 Dense([256,128][i]), 
-                Dropout(0.5)            # dropout scheduling is not supported in Python yet 
+                Dropout(0.5)
             ]), 
             Dense(num_classes, activation=None)
         ])(scaled_input)

Examples/Image/Classification/ConvNet/Python/ConvNet_MNIST.py

@@ -22,13 +22,12 @@ model_path = os.path.join(abs_path, "Models")
 # Define the reader for both training and evaluation action.
 def create_reader(path, is_training, input_dim, label_dim):
     return MinibatchSource(CTFDeserializer(path, StreamDefs(
-        features  = StreamDef(field='features', shape=input_dim, is_sparse=False),
-        labels    = StreamDef(field='labels',   shape=label_dim, is_sparse=False)
+        features  = StreamDef(field='features', shape=input_dim),
+        labels    = StreamDef(field='labels',   shape=label_dim)
     )), randomize=is_training, epoch_size = INFINITELY_REPEAT if is_training else FULL_DATA_SWEEP)
 
 
 # Creates and trains a feedforward classification model for MNIST images
-
 def convnet_mnist(debug_output=False):
     image_height = 28
     image_width  = 28

Examples/Image/Classification/ConvNet/README.md

@@ -13,7 +13,7 @@
 
 ### Getting the data
 
-We use the MNIST and CIFAR-10 datasets to demonstrate how to train a `convolutional neural network (CNN)`. CNN has been one of the most popular neural networks for image-related tasks. A very well-known early work on CNN is the [LeNet](http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf). In 2012 Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton won the ILSVRC-2012 competition using a [CNN architecture](https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf). And most state-of-the-art neural networks on image classification tasks today adopts a modified CNN architecture, such as [VGG](../VGG), [GoogLeNet](../GoogLeNet), [ResNet](../ResNet), etc.
+We use the MNIST and CIFAR-10 datasets to demonstrate how to train a `convolutional neural network (CNN)`. CNN has been one of the most popular neural networks for image-related tasks. A very well-known early work on CNN is the [LeNet](http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf). In 2012 Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton won the ILSVRC-2012 competition using a CNN architecture, [AlexNet](https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf). And most state-of-the-art neural networks on image classification tasks today adopt a modified CNN architecture, such as [VGG](../VGG), [GoogLeNet](../GoogLeNet), [ResNet](../ResNet), etc.
 
 MNIST and CIFAR-10 datasets are not included in the CNTK distribution but can be easily downloaded and converted by following the instructions in [DataSets/MNIST](../../DataSets/MNIST) and [DataSets/CIFAR-10](../../DataSets/CIFAR-10). We recommend you to keep the downloaded data in the respective folder while downloading, as the configuration files in this folder assumes that by default.