Migrating images in a tensor flow, changing a simple softmax layer to CNN multilayer

Question

Migrating images in a tensor flow, changing a simple softmax layer to CNN multilayer

Tensorflow has released a transmission training tutorial called Image retraining, which can be found here: https://www.tensorflow.org/tutorials/image_retraining

What they do is use a pre-prepared v3-based model, and then they change only the very last layer (softmax regression layer) and train it in a new dataset. This is very understandable and is actually a common practice in teaching transmission.

I tried my method in my data set (which is a small data set) and I applied all the suggestions to get the best result from increasing the data, to change the number of steps, but I did not modify their code in any way, Precision, which I received, relatively poor ~ 70%.

I think about the possibility of training a small neural network on top of this model, namely, changing the last layer from simple regression to a more complex network.

Here is the part of their code where they change the softmax layer:

def add_final_training_ops(class_count, final_tensor_name, bottleneck_tensor):
  """Adds a new softmax and fully-connected layer for training.
  We need to retrain the top layer to identify our new classes, so this function
  adds the right operations to the graph, along with some variables to hold the
  weights, and then sets up all the gradients for the backward pass.
  The set up for the softmax and fully-connected layers is based on:
  https://tensorflow.org/versions/master/tutorials/mnist/beginners/index.html
  Args:
    class_count: Integer of how many categories of things we're trying to
    recognize.
    final_tensor_name: Name string for the new final node that produces results.
    bottleneck_tensor: The output of the main CNN graph.
  Returns:
    The tensors for the training and cross entropy results, and tensors for the
    bottleneck input and ground truth input.
  """
  with tf.name_scope('input'):
    bottleneck_input = tf.placeholder_with_default(
        bottleneck_tensor, shape=[None, BOTTLENECK_TENSOR_SIZE],
        name='BottleneckInputPlaceholder')

    ground_truth_input = tf.placeholder(tf.float32,
                                        [None, class_count],
                                        name='GroundTruthInput')

  # Organizing the following ops as `final_training_ops` so they're easier
  # to see in TensorBoard
  layer_name = 'final_training_ops'
  with tf.name_scope(layer_name):
    with tf.name_scope('weights'):
      layer_weights = tf.Variable(tf.truncated_normal([BOTTLENECK_TENSOR_SIZE, class_count], stddev=0.001), name='final_weights')
      variable_summaries(layer_weights)
    with tf.name_scope('biases'):
      layer_biases = tf.Variable(tf.zeros([class_count]), name='final_biases')
      variable_summaries(layer_biases)
    with tf.name_scope('Wx_plus_b'):
      logits = tf.matmul(bottleneck_input, layer_weights) + layer_biases
      tf.summary.histogram('pre_activations', logits)

  final_tensor = tf.nn.softmax(logits, name=final_tensor_name)
  tf.summary.histogram('activations', final_tensor)

  with tf.name_scope('cross_entropy'):
    cross_entropy = tf.nn.softmax_cross_entropy_with_logits(
        labels=ground_truth_input, logits=logits)
    with tf.name_scope('total'):
      cross_entropy_mean = tf.reduce_mean(cross_entropy)
  tf.summary.scalar('cross_entropy', cross_entropy_mean)

  with tf.name_scope('train'):
    train_step = tf.train.GradientDescentOptimizer(FLAGS.learning_rate).minimize(
        cross_entropy_mean)

  return (train_step, cross_entropy_mean, bottleneck_input, ground_truth_input,
          final_tensor)


def add_evaluation_step(result_tensor, ground_truth_tensor):
  """Inserts the operations we need to evaluate the accuracy of our results.

  Args:
    result_tensor: The new final node that produces results.
    ground_truth_tensor: The node we feed ground truth data
    into.

  Returns:
    Tuple of (evaluation step, prediction).
  """
  with tf.name_scope('accuracy'):
    with tf.name_scope('correct_prediction'):
      prediction = tf.argmax(result_tensor, 1)
      correct_prediction = tf.equal(
          prediction, tf.argmax(ground_truth_tensor, 1))
    with tf.name_scope('accuracy'):
      evaluation_step = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
  tf.summary.scalar('accuracy', evaluation_step)
  return evaluation_step, prediction