diff options
author | Mark Daoust <markdaoust@google.com> | 2017-06-27 15:51:03 -0700 |
---|---|---|
committer | TensorFlower Gardener <gardener@tensorflow.org> | 2017-06-27 15:55:04 -0700 |
commit | 824dae164fcce971689e621e28ce62a92a84fdd7 (patch) | |
tree | 924db83495919803b44f0bc2414516fc79a578ad /tensorflow/examples/tutorials | |
parent | 7dede8848d0903a17ded277392f39f6f452fed28 (diff) |
Add name_scopes to mnist_deep.py for a cleaner graph layout.
PiperOrigin-RevId: 160338775
Diffstat (limited to 'tensorflow/examples/tutorials')
-rw-r--r-- | tensorflow/examples/tutorials/mnist/mnist_deep.py | 61 |
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()) |