wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-07-17 11:32:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

[tune] Added Async HyperBand example (#1709)

Browse Source
This commit is contained in:
Richard Liaw
2018-03-16 13:25:29 -07:00
committed by GitHub
parent d8adfbd440
commit 9b361115c3
3 changed files with 245 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/ray/tune/async_hyperband.py
+5 -1
View File
@@ -129,7 +129,11 @@ class _Bracket():
cutoff = self.cutoff(recorded)
if cutoff is not None and cur_rew < cutoff:
action = TrialScheduler.STOP
recorded[trial.trial_id] = cur_rew
if cur_rew is None:
print("Reward attribute is None! Consider"
" reporting using a different field.")
else:
recorded[trial.trial_id] = cur_rew
break
return action
python/ray/tune/examples/tune_mnist_async_hyperband.py
Executable
+235
View File
@@ -0,0 +1,235 @@
#!/usr/bin/env python
#
# Copyright 2015 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.
# ==============================================================================
"""A deep MNIST classifier using convolutional layers.
See extensive documentation at
https://www.tensorflow.org/get_started/mnist/pros
"""
# Disable linter warnings to maintain consistency with tutorial.
# pylint: disable=invalid-name
# pylint: disable=g-bad-import-order
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import sys
import tempfile
import time
import ray
from ray.tune import grid_search, run_experiments, register_trainable
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
FLAGS = None
status_reporter = None # used to report training status back to Ray
activation_fn = None # e.g. tf.nn.relu
def deepnn(x):
"""deepnn builds the graph for a deep net for classifying digits.
Args:
x: an input tensor with the dimensions (N_examples, 784), where 784 is
the number of pixels in a standard MNIST image.
Returns:
A tuple (y, keep_prob). y is a tensor of shape (N_examples, 10), with
values equal to the logits of classifying the digit into one of 10
classes (the digits 0-9). keep_prob is a scalar placeholder for the
probability of dropout.
"""
# Reshape to use within a convolutional neural net.
# Last dimension is for "features" - there is only one here, since images
# are grayscale -- it would be 3 for an RGB image, 4 for RGBA, etc.
with tf.name_scope('reshape'):
x_image = tf.reshape(x, [-1, 28, 28, 1])
# First convolutional layer - maps one grayscale image to 32 feature maps.
with tf.name_scope('conv1'):
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
h_conv1 = activation_fn(conv2d(x_image, W_conv1) + b_conv1)
# Pooling layer - downsamples by 2X.
with tf.name_scope('pool1'):
h_pool1 = max_pool_2x2(h_conv1)
# Second convolutional layer -- maps 32 feature maps to 64.
with tf.name_scope('conv2'):
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = activation_fn(conv2d(h_pool1, W_conv2) + b_conv2)
# Second pooling layer.
with tf.name_scope('pool2'):
h_pool2 = max_pool_2x2(h_conv2)
# Fully connected layer 1 -- after 2 round of downsampling, our 28x28 image
# is down to 7x7x64 feature maps -- maps this to 1024 features.
with tf.name_scope('fc1'):
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = activation_fn(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# Dropout - controls the complexity of the model, prevents co-adaptation of
# features.
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# Map the 1024 features to 10 classes, one for each digit
with tf.name_scope('fc2'):
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
return y_conv, keep_prob
def conv2d(x, W):
"""conv2d returns a 2d convolution layer with full stride."""
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
"""max_pool_2x2 downsamples a feature map by 2X."""
return tf.nn.max_pool(
x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
def weight_variable(shape):
"""weight_variable generates a weight variable of a given shape."""
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
"""bias_variable generates a bias variable of a given shape."""
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def main(_):
# Import data
for _ in range(10):
try:
mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)
break
except Exception:
time.sleep(5)
# Create the model
x = tf.placeholder(tf.float32, [None, 784])
# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 10])
# Build the graph for the deep net
y_conv, keep_prob = deepnn(x)
with tf.name_scope('loss'):
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(
labels=y_, logits=y_conv)
cross_entropy = tf.reduce_mean(cross_entropy)
with tf.name_scope('adam_optimizer'):
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
with tf.name_scope('accuracy'):
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
correct_prediction = tf.cast(correct_prediction, tf.float32)
accuracy = tf.reduce_mean(correct_prediction)
graph_location = tempfile.mkdtemp()
print('Saving graph to: %s' % graph_location)
train_writer = tf.summary.FileWriter(graph_location)
train_writer.add_graph(tf.get_default_graph())
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(20000):
batch = mnist.train.next_batch(50)
if i % 10 == 0:
train_accuracy = accuracy.eval(feed_dict={
x: batch[0], y_: batch[1], keep_prob: 1.0})
# !!! Report status to ray.tune !!!
if status_reporter:
status_reporter(
timesteps_total=i, mean_accuracy=train_accuracy)
print('step %d, training accuracy %g' % (i, train_accuracy))
train_step.run(
feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print('test accuracy %g' % accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
# !!! Entrypoint for ray.tune !!!
def train(config={'activation': 'relu'}, reporter=None):
global FLAGS, status_reporter, activation_fn
status_reporter = reporter
activation_fn = getattr(tf.nn, config['activation'])
parser = argparse.ArgumentParser()
parser.add_argument(
'--data_dir', type=str, default='/tmp/tensorflow/mnist/input_data',
help='Directory for storing input data')
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
# !!! Example of using the ray.tune Python API !!!
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument(
'--smoke-test', action='store_true', help='Finish quickly for testing')
args, _ = parser.parse_known_args()
register_trainable('train_mnist', train)
mnist_spec = {
'run': 'train_mnist',
'repeat': 10,
'stop': {
'mean_accuracy': 0.99,
'timesteps_total': 600,
},
'config': {
'activation': grid_search(['relu', 'elu', 'tanh']),
},
}
if args.smoke_test:
mnist_spec['stop']['training_iteration'] = 2
mnist_spec['repeat'] = 1
ray.init()
from ray.tune.async_hyperband import AsyncHyperBandScheduler
run_experiments({'tune_mnist_test': mnist_spec},
scheduler=AsyncHyperBandScheduler(
time_attr="timesteps_total",
reward_attr="mean_accuracy",
max_t=600,))