Trying to log accuracy of CNN TensorFlow on TensorBoard

Question

I have modified the a CNN tensorflow model for image classification to include higher number convolutional layers. It is working fine. I want to log the accuracy of the model every 50 steps using the TensorBoard. I have been trying to add FileWriter but no luck. Can you help me on how should I do it.

Thanks Here is my code:

"""Convolutional Neural Network Estimator for MNIST, built with tf.layers."""
import numpy as np
import tensorflow as tf
tf.logging.set_verbosity(tf.logging.INFO)


def cnn_model_fn(features, labels, mode):
  """Model function for CNN."""
  input_layer = tf.reshape(features["x"], [-1, 28, 28, 1])

  # Convolutional Layer #1
  conv1 = tf.layers.conv2d(...)

  # Pooling Layer #1
  pool1 = tf.layers.max_pooling2d(...)


  # Flatten tensor into a batch of vectors
  pool2_flat = tf.reshape(...)

  # Dense Layer
  dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)

  # Add dropout operation; 0.6 probability that element will be kept
  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)

  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
  .
  .
  .

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

  # 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)

  # Train the model
  train_input_fn = tf.estimator.inputs.numpy_input_fn(
      x={"x": train_data},
      y=train_labels,
      batch_size=100,
      num_epochs=None,
      shuffle=True)

  mnist_classifier.train(
      input_fn=train_input_fn,
      steps=2000,
      hooks=[logging_hook])

  # Evaluate the model and print results
  eval_input_fn = tf.estimator.inputs.numpy_input_fn(
      x={"x": eval_data},
      y=eval_labels,
      num_epochs=1,
      shuffle=False)
  eval_results = mnist_classifier.evaluate(input_fn=eval_input_fn)
  print(eval_results)


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

Answer 1

For training with tf.estimatorEstimator, you don't really need to write summary with a FileWriter. It will merge all summaries and save them every few steps. By default, it is every 100 steps. To log the accuracy during training, you just need to define the summary operation for your TRAIN mode like this:

accuracy = tf.metrics.accuracy(
    labels=labels, predictions=predictions["classes"])
tf.summary.scalar('accuracy', accuracy[1])

If you want to do every 50, you will need to change the default behavior by passing config during estimator instantiation like this:

mnist_classifier = tf.estimator.Estimator(
    model_fn=cnn_model_fn, model_dir="/tmp/mnist_convnet_model",
    config=tf.estimator.RunConfig(save_summary_steps=50))

You should now be able to see the accuracy of your model every 50 steps using the TensorBoard.