Add name_scopes to mnist_deep.py for a cleaner graph layout.

PiperOrigin-RevId: 160338775

1 files changed, 38 insertions, 23 deletions

diff --git a/tensorflow/examples/tutorials/mnist/mnist_deep.py b/tensorflow/examples/tutorials/mnist/mnist_deep.py
index 2896eee77d..4df925c1f3 100644
--- a/tensorflow/examples/tutorials/mnist/mnist_deep.py
+++ b/tensorflow/examples/tutorials/mnist/mnist_deep.py
@@ -52,42 +52,50 @@ def deepnn(x):
   # Reshape to use within a convolutional neural net.
   # Last dimension is for "features" - there is only one here, since images are
   # grayscale -- it would be 3 for an RGB image, 4 for RGBA, etc.
-  x_image = tf.reshape(x, [-1, 28, 28, 1])
+  with tf.name_scope('reshape'):
+    x_image = tf.reshape(x, [-1, 28, 28, 1])
 
   # First convolutional layer - maps one grayscale image to 32 feature maps.
-  W_conv1 = weight_variable([5, 5, 1, 32])
-  b_conv1 = bias_variable([32])
-  h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
+  with tf.name_scope('conv1'):
+    W_conv1 = weight_variable([5, 5, 1, 32])
+    b_conv1 = bias_variable([32])
+    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
 
   # Pooling layer - downsamples by 2X.
-  h_pool1 = max_pool_2x2(h_conv1)
+  with tf.name_scope('pool1'):
+    h_pool1 = max_pool_2x2(h_conv1)
 
   # Second convolutional layer -- maps 32 feature maps to 64.
-  W_conv2 = weight_variable([5, 5, 32, 64])
-  b_conv2 = bias_variable([64])
-  h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
+  with tf.name_scope('conv2'):
+    W_conv2 = weight_variable([5, 5, 32, 64])
+    b_conv2 = bias_variable([64])
+    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
 
   # Second pooling layer.
-  h_pool2 = max_pool_2x2(h_conv2)
+  with tf.name_scope('pool2'):
+    h_pool2 = max_pool_2x2(h_conv2)
 
   # Fully connected layer 1 -- after 2 round of downsampling, our 28x28 image
   # is down to 7x7x64 feature maps -- maps this to 1024 features.
-  W_fc1 = weight_variable([7 * 7 * 64, 1024])
-  b_fc1 = bias_variable([1024])
+  with tf.name_scope('fc1'):
+    W_fc1 = weight_variable([7 * 7 * 64, 1024])
+    b_fc1 = bias_variable([1024])
 
-  h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
-  h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
+    h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
+    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
 
   # Dropout - controls the complexity of the model, prevents co-adaptation of
   # features.
-  keep_prob = tf.placeholder(tf.float32)
-  h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
+  with tf.name_scope('dropout'):
+    keep_prob = tf.placeholder(tf.float32)
+    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
 
   # Map the 1024 features to 10 classes, one for each digit
-  W_fc2 = weight_variable([1024, 10])
-  b_fc2 = bias_variable([10])
+  with tf.name_scope('fc2'):
+    W_fc2 = weight_variable([1024, 10])
+    b_fc2 = bias_variable([10])
 
-  y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
+    y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
   return y_conv, keep_prob
 
 
@@ -127,11 +135,18 @@ def main(_):
   # Build the graph for the deep net
   y_conv, keep_prob = deepnn(x)
 
-  cross_entropy = tf.reduce_mean(
-      tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
-  train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
-  correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
-  accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
+  with tf.name_scope('loss'):
+    cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_,
+                                                            logits=y_conv)
+  cross_entropy = tf.reduce_mean(cross_entropy)
+
+  with tf.name_scope('adam_optimizer'):
+    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
+
+  with tf.name_scope('accuracy'):
+    correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
+    correct_prediction = tf.cast(correct_prediction, tf.float32)
+  accuracy = tf.reduce_mean(correct_prediction)
 
   with tf.Session() as sess:
     sess.run(tf.global_variables_initializer())