CODEWITHSUNDEEP
tensorflowtf-slim
Wei Liu
Wei Liu

Reputation: 1

How to print predictions in TF-Slim's eval_image_classifier.py?

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

import math
import tensorflow as tf

from datasets import dataset_factory
from nets import nets_factory
from preprocessing import preprocessing_factory

slim = tf.contrib.slim

tf.app.flags.DEFINE_integer(
    'batch_size', 100, 'The number of samples in each batch.')

tf.app.flags.DEFINE_integer(
    'max_num_batches', None,
    'Max number of batches to evaluate by default use all.')

tf.app.flags.DEFINE_string(
    'master', '', 'The address of the TensorFlow master to use.')

tf.app.flags.DEFINE_string(
    'checkpoint_path', '/tmp/tfmodel/',
    'The directory where the model was written to or an absolute path to a '
    'checkpoint file.')

tf.app.flags.DEFINE_string(
    'eval_dir', '/tmp/tfmodel/', 'Directory where the results are saved to.')

tf.app.flags.DEFINE_integer(
    'num_preprocessing_threads', 4,
    'The number of threads used to create the batches.')

tf.app.flags.DEFINE_string(
    'dataset_name', 'imagenet', 'The name of the dataset to load.')

tf.app.flags.DEFINE_string(
    'dataset_split_name', 'test', 'The name of the train/test split.')

tf.app.flags.DEFINE_string(
    'dataset_dir', None, 'The directory where the dataset files are stored.')

tf.app.flags.DEFINE_integer(
    'labels_offset', 0,
    'An offset for the labels in the dataset. This flag is primarily used to '
    'evaluate the VGG and ResNet architectures which do not use a background '
    'class for the ImageNet dataset.')

tf.app.flags.DEFINE_string(
    'model_name', 'inception_v3', 'The name of the architecture to evaluate.')

tf.app.flags.DEFINE_string(
    'preprocessing_name', None, 'The name of the preprocessing to use. If left '
    'as `None`, then the model_name flag is used.')

tf.app.flags.DEFINE_float(
    'moving_average_decay', None,
    'The decay to use for the moving average.'
    'If left as None, then moving averages are not used.')

tf.app.flags.DEFINE_integer(
    'eval_image_size', None, 'Eval image size')

FLAGS = tf.app.flags.FLAGS


def main(_):
  if not FLAGS.dataset_dir:
    raise ValueError('You must supply the dataset directory with --dataset_dir')

  tf.logging.set_verbosity(tf.logging.INFO)
  with tf.Graph().as_default():
    tf_global_step = slim.get_or_create_global_step()

    ######################
    # Select the dataset #
    ######################
    dataset = dataset_factory.get_dataset(
        FLAGS.dataset_name, FLAGS.dataset_split_name, FLAGS.dataset_dir)

    ####################
    # Select the model #
    ####################
    network_fn = nets_factory.get_network_fn(
        FLAGS.model_name,
        num_classes=(dataset.num_classes - FLAGS.labels_offset),
        is_training=False)

    ##############################################################
    # Create a dataset provider that loads data from the dataset #
    ##############################################################
    provider = slim.dataset_data_provider.DatasetDataProvider(
        dataset,
        shuffle=False,
        common_queue_capacity=2 * FLAGS.batch_size,
        common_queue_min=FLAGS.batch_size)
    [image, label] = provider.get(['image', 'label'])
    label -= FLAGS.labels_offset

    #####################################
    # Select the preprocessing function #
    #####################################
    preprocessing_name = FLAGS.preprocessing_name or FLAGS.model_name
    image_preprocessing_fn = preprocessing_factory.get_preprocessing(
        preprocessing_name,
        is_training=False)

    eval_image_size = FLAGS.eval_image_size or network_fn.default_image_size

    image = image_preprocessing_fn(image, eval_image_size, eval_image_size)

    images, labels = tf.train.batch(
        [image, label],
        batch_size=FLAGS.batch_size,
        num_threads=FLAGS.num_preprocessing_threads,
        capacity=5 * FLAGS.batch_size)

    ####################
    # Define the model #
    ####################
    logits, _ = network_fn(images)

    if FLAGS.moving_average_decay:
      variable_averages = tf.train.ExponentialMovingAverage(
          FLAGS.moving_average_decay, tf_global_step)
      variables_to_restore = variable_averages.variables_to_restore(
          slim.get_model_variables())
      variables_to_restore[tf_global_step.op.name] = tf_global_step
    else:
      variables_to_restore = slim.get_variables_to_restore()

    predictions = tf.argmax(logits, 1)
    labels = tf.squeeze(labels)

    # Define the metrics:
    names_to_values, names_to_updates = slim.metrics.aggregate_metric_map({
        'Accuracy': slim.metrics.streaming_accuracy(predictions, labels),
        'Recall_5': slim.metrics.streaming_recall_at_k(
            logits, labels, 5),
    })

    # Print the summaries to screen.
    for name, value in names_to_values.items():
      summary_name = 'eval/%s' % name
      op = tf.summary.scalar(summary_name, value, collections=[])
      op = tf.Print(op, [value], summary_name)
      tf.add_to_collection(tf.GraphKeys.SUMMARIES, op)

    # TODO(sguada) use num_epochs=1
    if FLAGS.max_num_batches:
      num_batches = FLAGS.max_num_batches
    else:
      # This ensures that we make a single pass over all of the data.
      num_batches = math.ceil(dataset.num_samples / float(FLAGS.batch_size))

    if tf.gfile.IsDirectory(FLAGS.checkpoint_path):
      checkpoint_path = tf.train.latest_checkpoint(FLAGS.checkpoint_path)
    else:
      checkpoint_path = FLAGS.checkpoint_path

    tf.logging.info('Evaluating %s' % checkpoint_path)

    slim.evaluation.evaluate_once(
        master=FLAGS.master,
        checkpoint_path=checkpoint_path,
        logdir=FLAGS.eval_dir,
        num_evals=num_batches,
        eval_op=list(names_to_updates.values()),
        variables_to_restore=variables_to_restore)


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

https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/slim/python/slim/evaluation.py

Hi, guys!

I want to get classification prediction results for batches of images by using tensorflow slim.

I have tried lots of way for a long time, but I failed to print or write "predictions" into file such as aaa.txt. How can do it?

Thank you in advance.

Upvotes: 0

Views: 1064

Answers (1)

sabhiram
sabhiram

Reputation: 907

This is a common issue. The reason you are having trouble is because there are two states for each operator that is defined the graph above. In the python code as it executes, you define your operators and specify their input tensors and output tensors -- you are building the graph per se. The other state is what you are interested in, which is the value of the data as it enters the op on any given pass through your graph.

During the slim.evaluation.evaluate_once and other such methods, the graph is run for one batch and all the operations defined get executed as the processor makes its way through your graph definition.

The simplest thing to do (if all you want is prints) is to get familiar with the tf.Print operator which allows you to observe the contents of a tensor (or n tensors) as they are evaluated. The catch here is you need to make sure that the graph includes the operator for the Print in its definition so that the print actually knows what the tensor values are per pass.

Another method if you need custom reporting is to create a custom PyOp which sits in the graph definition as a no-op (input tensors == output tensors, or the node has no outputs), depending on how your graph is defined. Once you are in py code - you get access to the input tensors in a python context as numpy arrays (I think). Here is a small utility I wrote a while back when I was playing with slim to dump base64 images along with the correct / incorrect prediction classes to a report (html file) after every run. Warning shameless self plug: https://github.com/sabhiram/tf-eval-reporter

Upvotes: 1

Related Questions