tfrecord_image_decode.py

# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Generic training script that trains a model using a given dataset."""

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

import tensorflow as tf

import matplotlib.pyplot as plt
import cv2
import numpy as np

import os
import sys

# This is needed since the notebook is stored in the object_detection folder.
TF_API="/home/robin/eclipse-workspace-python/TF_models/models/research/slim"
sys.path.append(os.path.split(TF_API)[0])
sys.path.append(TF_API)

from datasets import dataset_factory
from deployment import model_deploy
from nets import nets_factory
from preprocessing import preprocessing_factory
from datasets import dataset_utils

slim = tf.contrib.slim

tf.app.flags.DEFINE_integer('num_clones', 1,
                            'Number of model clones to deploy. Note For '
                            'historical reasons loss from all clones averaged '
                            'out and learning rate decay happen per clone '
                            'epochs')

tf.app.flags.DEFINE_boolean('clone_on_cpu', False,
                            'Use CPUs to deploy clones.')

tf.app.flags.DEFINE_integer('worker_replicas', 1, 'Number of worker replicas.')

tf.app.flags.DEFINE_integer(
    'num_ps_tasks', 0,
    'The number of parameter servers. If the value is 0, then the parameters '
    'are handled locally by the worker.')

tf.app.flags.DEFINE_integer(
    'num_readers', 4,
    'The number of parallel readers that read data from the dataset.')

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

tf.app.flags.DEFINE_integer(
    'task', 0, 'Task id of the replica running the training.')

######################
# Optimization Flags #
######################

tf.app.flags.DEFINE_float(
    'weight_decay', 0.00004, 'The weight decay on the model weights.')

#######################
# Dataset Flags #
#######################

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

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

tf.app.flags.DEFINE_string(
    'dataset_dir', "/home/robin/Dataset/imaget/output_tfrecord", '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_v1', 'The name of the architecture to train.')

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_integer(
    'batch_size', 12, 'The number of samples in each batch.')

tf.app.flags.DEFINE_integer(
    'train_image_size', None, 'Train image size')

tf.app.flags.DEFINE_integer('max_number_of_steps', None,
                            'The maximum number of training steps.')

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():
    #######################
    # Config model_deploy #
    #######################
    deploy_config = model_deploy.DeploymentConfig(
        num_clones=FLAGS.num_clones,
        clone_on_cpu=FLAGS.clone_on_cpu,
        replica_id=FLAGS.task,
        num_replicas=FLAGS.worker_replicas,
        num_ps_tasks=FLAGS.num_ps_tasks)

    # Create global_step
    with tf.device(deploy_config.variables_device()):
      global_step = slim.create_global_step()

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

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

    #####################################
    # 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)

    ##############################################################
    # Create a dataset provider that loads data from the dataset #
    ##############################################################
    with tf.device(deploy_config.inputs_device()):
      provider = slim.dataset_data_provider.DatasetDataProvider(
          dataset,
          num_readers=FLAGS.num_readers,
          common_queue_capacity=20 * FLAGS.batch_size,
          common_queue_min=10 * FLAGS.batch_size)
      [image, label] = provider.get(['image', 'label'])
      label -= FLAGS.labels_offset

      train_image_size = FLAGS.train_image_size or network_fn.default_image_size
      print(train_image_size)

      image = image_preprocessing_fn(image, train_image_size, train_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)
      labels = slim.one_hot_encoding(
          labels, dataset.num_classes - FLAGS.labels_offset)
      batch_queue = slim.prefetch_queue.prefetch_queue(
          [images, labels], capacity=2 * deploy_config.num_clones)
      
      
    images, labels = batch_queue.dequeue()
    print(images, labels)
    logits, end_points = network_fn(images)
     
    
    labels_to_class_names = dataset_utils.read_label_file(FLAGS.dataset_dir, filename='labels.txt')
    print(labels_to_class_names)

    
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        
        coord=tf.train.Coordinator()     
        threads= tf.train.start_queue_runners(coord=coord)

        images_np, labels_np = sess.run([images, labels])
        print(images_np.shape, labels_np.shape)
        
        for i in range(10):
            image_np,label_np=sess.run([images, labels])
            
#             plt.imshow(image_np[0,:,:,:])
#             plt.title('label name:'+str(label_np[0]))
#             plt.show()

            cv2.imshow('label name:',cv2.cvtColor(image_np[0,:,:,:],cv2.COLOR_RGB2BGR))
            print(labels_to_class_names[np.argmax(label_np[0])])
            cv2.waitKey(0)
        
        coord.request_stop()     
        coord.join(threads)

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