def main(argv=None):
global_step = tf.Variable(0, trainable=False)
files = [os.path.join(FLAGS.data_dir, 'data%d.tfrecords' % i) for i in range(1, 6)]
images, labels = v2.inputs(files, distort=True)
logits = v2.inference(images)
losses = v2.loss(logits, labels)
train_op = v2.train(losses, global_step)
summary_op = tf.merge_all_summaries()
saver = tf.train.Saver(tf.all_variables(), max_to_keep=10)
with tf.Session() as sess:
summary_writer = tf.train.SummaryWriter('train', graph_def=sess.graph_def)
sess.run(tf.initialize_all_variables())
tf.train.start_queue_runners(sess=sess)
for step in range(FLAGS.max_steps):
start_time = time.time()
_, loss_value = sess.run([train_op, losses])
duration = time.time() - start_time
assert not np.isnan(loss_value), 'Model diverged with loss = NaN'
format_str = '%s: step %d, loss = %.5f (%.3f sec/batch)'
print format_str % (datetime.now(), step, loss_value, duration)
if step % 100 == 0 or (step + 1) == FLAGS.max_steps:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
def main(argv=None):
files = [os.path.join(FLAGS.data_dir, "test.tfrecords")]
images, labels = v2.inputs(files, distort=False)
logits = v2.inference(images)
top_k_op = tf.nn.in_top_k(logits, labels, 1)
variable_averages = tf.train.ExponentialMovingAverage(v2.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
summary_op = tf.merge_all_summaries()
summary_writer = tf.train.SummaryWriter(FLAGS.eval_dir)
eval_once(saver, summary_writer, top_k_op, summary_op)
def main(argv=None):
files = [os.path.join(FLAGS.data_dir, 'test.tfrecords') for i in range(1, 2)]
images, labels = v2.inputs(files, distort=False)
logits = v2.inference(images)
top_k_op = tf.nn.in_top_k(logits, labels, 1)
variable_averages = tf.train.ExponentialMovingAverage(v2.MOVING_AVERAGE_DECAY)
variables_to_restore = {}
for v in tf.all_variables():
if v in tf.trainable_variables():
name = variable_averages.average_name(v)
else:
name = v.op.name
variables_to_restore[name] = v
saver = tf.train.Saver(variables_to_restore)
eval_once(saver, top_k_op)
from flask import Flask, jsonify, request
import tensorflow as tf
import base64
import urllib
import os
import gzip
v2.BATCH_SIZE = 1
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string("checkpoint_path", "/tmp/model.ckpt", """Directory where to read model checkpoints.""")
tf.app.flags.DEFINE_integer("port", 5000, """Application port.""")
images = tf.placeholder(tf.float32, shape=(1, v2.INPUT_SIZE, v2.INPUT_SIZE, 3))
logits = tf.nn.softmax(v2.inference(images))
sess = tf.Session()
variable_averages = tf.train.ExponentialMovingAverage(v2.MOVING_AVERAGE_DECAY)
variables_to_restore = {}
for v in tf.all_variables():
if v in tf.trainable_variables():
restore_name = variable_averages.average_name(v)
else:
restore_name = v.op.name
variables_to_restore[restore_name] = v
saver = tf.train.Saver(variables_to_restore)
if not os.path.isfile(FLAGS.checkpoint_path):
print "No checkpoint file found"
urllib.urlretrieve(os.environ["DOWNLOAD_URL"], FLAGS.checkpoint_path + ".gz")
open(FLAGS.checkpoint_path, "wb").write(gzip.open(FLAGS.checkpoint_path + ".gz").read())
