本文整理汇总了Python中Model.Model.create_graph方法的典型用法代码示例。如果您正苦于以下问题：Python Model.create_graph方法的具体用法？Python Model.create_graph怎么用？Python Model.create_graph使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类Model.Model的用法示例。
在下文中一共展示了Model.create_graph方法的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: DatasetLoader
# 需要导入模块: from Model import Model [as 别名]
# 或者: from Model.Model import create_graph [as 别名]
FLAGS = flags.FLAGS
flags.DEFINE_integer('batch_size', 100, 'batch size')
flags.DEFINE_string('test_files_glob', './input/test*.tfrecords', 'glob for TFRecords files containing testing data')
flags.DEFINE_string('model_file', './model.ckpt', 'path to load trained model parameters from')
flags.DEFINE_integer('read_threads', multiprocessing.cpu_count(), 'number of reading threads')
flags.DEFINE_string('summary', './tensorboard_test', 'Tensorboard output directory')
# Testing input
dataset_loader = DatasetLoader()
keep_prob_holder = tf.placeholder(tf.float32, shape = ())
image_batch, label_batch = dataset_loader.input_batch(
glob(FLAGS.test_files_glob), FLAGS.batch_size, FLAGS.read_threads)
label_batch = tf.cast(label_batch, tf.float32)
# Model, correctness predicate, and correctness aggregator
inferred_labels = Model.create_graph(image_batch, keep_prob_holder)
correct_prediction = tf.equal(tf.argmax(inferred_labels, 1), tf.argmax(tf.cast(label_batch, tf.float32), 1))
accuracy_op = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
correct_images = tf.boolean_mask(image_batch, correct_prediction)
incorrect_images = tf.boolean_mask(image_batch, tf.logical_not(correct_prediction))
tf.summary.image('Correct Inference', correct_images, max_outputs = 20)
tf.summary.image('Incorrect Inference', incorrect_images, max_outputs = 20)
# Run graph
average = Average()
TFRunner.run(
accuracy_op,
feed_dict = {keep_prob_holder: 1.0},
restore_checkpoint = FLAGS.model_file,
batch_result_callback = average.add,
summary = FLAGS.summary,示例2: Flask
# 需要导入模块: from Model import Model [as 别名]
# 或者: from Model.Model import create_graph [as 别名]
from flask import Flask, jsonify, render_template, request
import tensorflow as tf
import sys
sys.path.append('../train')
from Model import Model
app = Flask(__name__)
keep_prob_placeholder = tf.constant(1.0, tf.float32)
image_placeholder = tf.placeholder(tf.uint8, [None, 256, 256, 3])
output = Model.create_graph(image_placeholder, keep_prob_placeholder)
sess = tf.Session()
saver = tf.train.Saver(sharded=True)
saver.restore(sess, '../train/model.ckpt')
def infer(image):
return sess.run(output, feed_dict={image_placeholder: image}).flatten().tolist()
def process_jpeg(stream):
image = tf.image.decode_jpeg(stream.getvalue(), channels=3)
image.set_shape([258, 344, 3])
image = tf.image.resize_image_with_crop_or_pad(image, 256, 256)
image = tf.expand_dims(image, 0)
return image.eval(session = sess)
@app.route('/api/photo_orientation', methods=['POST'])