cifar_basic.py

# 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["x"], [-1, 32, 32, 3], name="input_tensor")

  # Convolutional Layer #1
  conv1 = tf.layers.conv2d(
      inputs=input_layer,
      filters=32,
      kernel_size=[7, 7],
      strides=(2, 2),
      padding="valid",
      activation=tf.nn.relu,
      name="conv1_tensor")
  
  # Dense Layer
  pool2_flat = tf.reshape(conv1, [-1, 5408])
  dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)
  dropout = tf.layers.dropout(
      inputs=dense, rate=0.4, training=mode == tf.estimator.ModeKeys.TRAIN)

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

  predictions = {
      # Generate predictions (for PREDICT and EVAL mode)
      "classes": tf.argmax(input=logits, axis=1),
      # Add `softmax_tensor` to the graph. It is used for PREDICT and by the
      # `logging_hook`.
      "probabilities": tf.nn.softmax(logits, name="softmax_tensor")
  }

  if mode == tf.estimator.ModeKeys.PREDICT:
    return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)

  # Calculate Loss (for both TRAIN and EVAL modes)
  loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)

  # Configure the Training Op (for TRAIN mode)
  if mode == tf.estimator.ModeKeys.TRAIN:
    optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001)
    train_op = optimizer.minimize(
        loss=loss,
        global_step=tf.train.get_global_step())
    return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)

  # Add evaluation metrics (for EVAL mode)
  eval_metric_ops = {
      "accuracy": tf.metrics.accuracy(
          labels=labels, predictions=predictions["classes"])}
  return tf.estimator.EstimatorSpec(
      mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
  
def main(unused_argv):
  # Load training and eval data
  #mnist = tf.contrib.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
  cifar_classifier = tf.estimator.Estimator(
      model_fn=cnn_model_fn, model_dir="cifar_convnet_model_2")

  # Set up logging for predictions
  # Log the values in the "Softmax" tensor with label "probabilities"
  tensors_to_log = {"probabilities": "softmax_tensor"}
  logging_hook = tf.train.LoggingTensorHook(
      tensors=tensors_to_log, every_n_iter=50)


  print("=============================")

  # Train the model
  train_input_fn = tf.estimator.inputs.numpy_input_fn(
      x={"x": train_data},
      y=train_labels,
      batch_size=100,
      num_epochs=100,
      shuffle=True)
  
  cifar_classifier.train(
      input_fn=train_input_fn,
      steps=200,
      hooks=[logging_hook])

  print("++++++++++++++++++++++++++++")
  
  # Evaluate the model and print results
  eval_input_fn = tf.estimator.inputs.numpy_input_fn(
      x={"x": train_data},
      y=train_labels,
      num_epochs=1,
      shuffle=False)
  
  eval_results = cifar_classifier.evaluate(input_fn=eval_input_fn)
  print(eval_results)
  print("##########################")
  
        
if __name__ == "__main__":
  tf.app.run()