###############################################
    ########### Defining place holders ############
    ###############################################
    image_place = tf.placeholder(tf.float32, shape=([None, height, width, num_channels]), name='image')
    label_place = tf.placeholder(tf.float32, shape=([None, FLAGS.num_classes]), name='gt')
    dropout_parameter = tf.placeholder(tf.float32)

    ##################################################
    ########### Model + loss + accuracy ##############
    ##################################################

    # MODEL
    joint_arg_scope = net.net_arg_scope(weight_decay=0.0005, is_training=FLAGS.is_training)
    with tf.contrib.framework.arg_scope(joint_arg_scope):
        logits_features, end_points = net.net_architecture(image_place, num_classes=FLAGS.num_classes,
                                                           dropout_keep_prob=dropout_parameter,
                                                           is_training=FLAGS.is_training)

    # Define loss
    with tf.name_scope('loss'):
        loss_test = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits_features, labels=label_place))

    # Accuracy
    with tf.name_scope('accuracy_test'):
        # Evaluate the model
        correct_test_prediction = tf.equal(tf.argmax(logits_features, 1), tf.argmax(label_place, 1))

        # Accuracy calculation
        accuracy_test = tf.reduce_mean(tf.cast(correct_test_prediction, tf.float32))

    ###############################################
    ###############################################
    ########### Defining place holders ############
    ###############################################
    image_place = tf.placeholder(tf.float32, shape=([None, height, width, num_channels]), name='image')
    label_place = tf.placeholder(tf.float32, shape=([None, FLAGS.num_classes]), name='gt')
    dropout_parameter = tf.placeholder(tf.float32)

    ##################################################
    ########### Model + loss + accuracy ##############
    ##################################################

    # MODEL
    joint_arg_scope = net.net_arg_scope(weight_decay=0.0005, is_training=FLAGS.is_training)
    with tf.contrib.framework.arg_scope(joint_arg_scope):
        logits_features, end_points = net.net_architecture(image_place, num_classes=FLAGS.num_classes,
                                                  dropout_keep_prob=dropout_parameter,
                                                  is_training=FLAGS.is_training)

    # Define loss
    with tf.name_scope('loss'):
        loss_test = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits_features, labels=label_place))

    # Accuracy
    with tf.name_scope('accuracy_test'):
        # Evaluate the model
        correct_test_prediction = tf.equal(tf.argmax(logits_features, 1), tf.argmax(label_place, 1))

        # Accuracy calculation
        accuracy_test = tf.reduce_mean(tf.cast(correct_test_prediction, tf.float32))

    ###############################################