In [2]:

    

# A Guide to TF Layers: Building a Convolutional Neural Network

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

# Imports
import numpy as np
import tensorflow as tf

from tensorflow.contrib import learn
from tensorflow.contrib.learn.python.learn.estimators import model_fn as model_fn_lib

tf.logging.set_verbosity(tf.logging.INFO)

# Our application logic will be added here
def cnn_model_fn(features, labels, mode):
  """Model function for CNN."""
  # Input Layer
  input_layer = tf.reshape(features, [-1, 28, 28, 1])

  # Convolutional Layer #1
  conv1 = tf.layers.conv2d(
      inputs=input_layer,
      filters=32,
      kernel_size=[5, 5],
      padding="same",
      activation=tf.nn.relu)

  # Pooling Layer #1
  pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)

  # Convolutional Layer #2 and Pooling Layer #2
  conv2 = tf.layers.conv2d(
      inputs=pool1,
      filters=64,
      kernel_size=[5, 5],
      padding="same",
      activation=tf.nn.relu)
  pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)

  # Dense Layer
  pool2_flat = tf.reshape(pool2, [-1, 7 * 7 * 64])
  dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)
  dropout = tf.layers.dropout(
      inputs=dense, rate=0.4, training=mode == learn.ModeKeys.TRAIN)

  # Logits Layer
  logits = tf.layers.dense(inputs=dropout, units=10)

  loss = None
  train_op = None

  # Calculate Loss (for both TRAIN and EVAL modes)
  if mode != learn.ModeKeys.INFER:
    onehot_labels = tf.one_hot(indices=tf.cast(labels, tf.int32), depth=10)
    loss = tf.losses.softmax_cross_entropy(
        onehot_labels=onehot_labels, logits=logits)

  # Configure the Training Op (for TRAIN mode)
  if mode == learn.ModeKeys.TRAIN:
    train_op = tf.contrib.layers.optimize_loss(
        loss=loss,
        global_step=tf.contrib.framework.get_global_step(),
        learning_rate=0.001,
        optimizer="SGD")

  # Generate Predictions
  predictions = {
      "classes": tf.argmax(
          input=logits, axis=1),
      "probabilities": tf.nn.softmax(
          logits, name="softmax_tensor")
  }

  # Return a ModelFnOps object
  return model_fn_lib.ModelFnOps(
      mode=mode, predictions=predictions, loss=loss, train_op=train_op)

def main(unused_argv):
  # Load training and eval data
  mnist = learn.datasets.load_dataset("mnist")
  train_data = mnist.train.images # Returns np.array
  train_labels = np.asarray(mnist.train.labels, dtype=np.int32)
  eval_data = mnist.test.images # Returns np.array
  eval_labels = np.asarray(mnist.test.labels, dtype=np.int32)

  # Create the Estimator
  mnist_classifier = learn.Estimator(
      model_fn=cnn_model_fn, model_dir="/tmp/mnist_convnet_model")

  # Set up logging for predictions
  tensors_to_log = {"probabilities": "softmax_tensor"}
  logging_hook = tf.train.LoggingTensorHook(
      tensors=tensors_to_log, every_n_iter=50)

  # Configure the accuracy metric for evaluation
  metrics = {
    "accuracy":
        learn.MetricSpec(
            metric_fn=tf.metrics.accuracy, prediction_key="classes"),
  }

  # Evaluate the model and print results
  eval_results = mnist_classifier.evaluate(
    x=eval_data, y=eval_labels, metrics=metrics)
  print(eval_results)

if __name__ == "__main__":
  tf.app.run()


    

    




Successfully downloaded train-images-idx3-ubyte.gz 9912422 bytes.
Extracting MNIST-data/train-images-idx3-ubyte.gz
Successfully downloaded train-labels-idx1-ubyte.gz 28881 bytes.
Extracting MNIST-data/train-labels-idx1-ubyte.gz
Successfully downloaded t10k-images-idx3-ubyte.gz 1648877 bytes.
Extracting MNIST-data/t10k-images-idx3-ubyte.gz
Successfully downloaded t10k-labels-idx1-ubyte.gz 4542 bytes.
Extracting MNIST-data/t10k-labels-idx1-ubyte.gz
INFO:tensorflow:Using default config.
INFO:tensorflow:Using config: {'_save_checkpoints_secs': 600, '_num_ps_replicas': 0, '_keep_checkpoint_max': 5, '_tf_random_seed': None, '_task_type': None, '_environment': 'local', '_is_chief': True, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x11b2b0050>, '_tf_config': gpu_options {
  per_process_gpu_memory_fraction: 1
}
, '_task_id': 0, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_evaluation_master': '', '_keep_checkpoint_every_n_hours': 10000, '_master': ''}
WARNING:tensorflow:From <ipython-input-2-a7cb42b00e80>:106: calling evaluate (from tensorflow.contrib.learn.python.learn.estimators.estimator) with y is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From <ipython-input-2-a7cb42b00e80>:106: calling evaluate (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
  est = Estimator(...) -> est = SKCompat(Estimator(...))






    




---------------------------------------------------------------------------
NotFittedError                            Traceback (most recent call last)
<ipython-input-2-a7cb42b00e80> in <module>()
    108 
    109 if __name__ == "__main__":
--> 110   tf.app.run()

/Users/lipingzhang/anaconda/lib/python2.7/site-packages/tensorflow/python/platform/app.pyc in run(main, argv)
     42   # Call the main function, passing through any arguments
     43   # to the final program.
---> 44   _sys.exit(main(_sys.argv[:1] + flags_passthrough))
     45 
     46 

<ipython-input-2-a7cb42b00e80> in main(unused_argv)
    104   # Evaluate the model and print results
    105   eval_results = mnist_classifier.evaluate(
--> 106     x=eval_data, y=eval_labels, metrics=metrics)
    107   print(eval_results)
    108 

/Users/lipingzhang/anaconda/lib/python2.7/site-packages/tensorflow/python/util/deprecation.pyc in new_func(*args, **kwargs)
    278             _call_location(), decorator_utils.get_qualified_name(func),
    279             func.__module__, arg_name, date, instructions)
--> 280       return func(*args, **kwargs)
    281     new_func.__doc__ = _add_deprecated_arg_notice_to_docstring(
    282         func.__doc__, date, instructions)

/Users/lipingzhang/anaconda/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.pyc in evaluate(self, x, y, input_fn, feed_fn, batch_size, steps, metrics, name, checkpoint_path, hooks, log_progress)
    499     _verify_input_args(x, y, input_fn, feed_fn, batch_size)
    500     if x is not None:
--> 501       return SKCompat(self).score(x, y, batch_size, steps, metrics)
    502 
    503     if metrics is not None and not isinstance(metrics, dict):

/Users/lipingzhang/anaconda/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.pyc in score(self, x, y, batch_size, steps, metrics)
   1366         steps=steps,
   1367         metrics=metrics,
-> 1368         name='score')
   1369     if eval_results is not None:
   1370       eval_results.update({'global_step': global_step})

/Users/lipingzhang/anaconda/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.pyc in _evaluate_model(self, input_fn, steps, feed_fn, metrics, name, checkpoint_path, hooks, log_progress)
    788       if not latest_path:
    789         raise NotFittedError("Couldn't find trained model at %s."
--> 790                              % self._model_dir)
    791       checkpoint_path = latest_path
    792 

NotFittedError: Couldn't find trained model at /tmp/mnist_convnet_model.

In [ ]: