TensorFlow Mechanics 101
2018-01-18 22:26
363 查看
ls
# %load fully_connected_feed.py # 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. # ============================================================================== import os os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID" os.environ["CUDA_VISIBLE_DEVICES"] = "3" """Trains and Evaluates the MNIST network using a feed dictionary.""" from __future__ import absolute_import from __future__ import division from __future__ import print_function # pylint: disable=missing-docstring import argparse import os import sys import time from six.moves import xrange # pylint: disable=redefined-builtin import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data from tensorflow.examples.tutorials.mnist import mnist # Basic model parameters as external flags. FLAGS = None def placeholder_inputs(batch_size): """Generate placeholder variables to represent the input tensors. These placeholders are used as inputs by the rest of the model building code and will be fed from the downloaded data in the .run() loop, below. Args: batch_size: The batch size will be baked into both placeholders. Returns: images_placeholder: Images placeholder. labels_placeholder: Labels placeholder. """ # Note that the shapes of the placeholders match the shapes of the full # image and label tensors, except the first dimension is now batch_size # rather than the full size of the train or test data sets. images_placeholder = tf.placeholder(tf.float32, shape=(batch_size, mnist.IMAGE_PIXELS)) labels_placeholder = tf.placeholder(tf.int32, shape=(batch_size)) return images_placeholder, labels_placeholder def fill_feed_dict(data_set, images_pl, labels_pl): """Fills the feed_dict for training the given step. A feed_dict takes the form of: feed_dict = { <placeholder>: <tensor of values to be passed for placeholder>, .... } Args: data_set: The set of images and labels, from input_data.read_data_sets() images_pl: The images placeholder, from placeholder_inputs(). labels_pl: The labels placeholder, from placeholder_inputs(). Returns: feed_dict: The feed dictionary mapping from placeholders to values. """ # Create the feed_dict for the placeholders filled with the next # `batch size` examples. images_feed, labels_feed = data_set.next_batch(FLAGS.batch_size, FLAGS.fake_data) feed_dict = { images_pl: images_feed, labels_pl: labels_feed, } return feed_dict def do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_set): """Runs one evaluation against the full epoch of data. Args: sess: The session in which the model has been trained. eval_correct: The Tensor that returns the number of correct predictions. images_placeholder: The images placeholder. labels_placeholder: The labels placeholder. data_set: The set of images and labels to evaluate, from input_data.read_data_sets(). """ # And run one epoch of eval. true_count = 0 # Counts the number of correct predictions. steps_per_epoch = data_set.num_examples // FLAGS.batch_size num_examples = steps_per_epoch * FLAGS.batch_size for step in xrange(steps_per_epoch): feed_dict = fill_feed_dict(data_set, images_placeholder, labels_placeholder) true_count += sess.run(eval_correct, feed_dict=feed_dict) precision = float(true_count) / num_examples print(' Num examples: %d Num correct: %d Precision @ 1: %0.04f' % (num_examples, true_count, precision)) def run_training(): """Train MNIST for a number of steps.""" # Get the sets of images and labels for training, validation, and # test on MNIST. data_sets = input_data.read_data_sets(FLAGS.input_data_dir, FLAGS.fake_data) # Tell TensorFlow that the model will be built into the default Graph. with tf.Graph().as_default(): # Generate placeholders for the images and labels. images_placeholder, labels_placeholder = placeholder_inputs( FLAGS.batch_size) # Build a Graph that computes predictions from the inference model. logits = mnist.inference(images_placeholder, FLAGS.hidden1, FLAGS.hidden2) # Add to the Graph the Ops for loss calculation. loss = mnist.loss(logits, labels_placeholder) # Add to the Graph the Ops that calculate and apply gradients. train_op = mnist.training(loss, FLAGS.learning_rate) # Add the Op to compare the logits to the labels during evaluation. eval_correct = mnist.evaluation(logits, labels_placeholder) # Build the summary Tensor based on the TF collection of Summaries. summary = tf.summary.merge_all() # Add the variable initializer Op. init = tf.global_variables_initializer() # Create a saver for writing training checkpoints. saver = tf.train.Saver() # Create a session for running Ops on the Graph. sess = tf.Session() # Instantiate a SummaryWriter to output summaries and the Graph. summary_writer = tf.summary.FileWriter(FLAGS.log_dir, sess.graph) # And then after everything is built: # Run the Op to initialize the variables. sess.run(init) # Start the training loop. for step in xrange(FLAGS.max_steps): start_time = time.time() # Fill a feed dictionary with the actual set of images and labels # for this particular training step. feed_dict = fill_feed_dict(data_sets.train, images_placeholder, labels_placeholder) # Run one step of the model. The return values are the activations # from the `train_op` (which is discarded) and the `loss` Op. To # inspect the values of your Ops or variables, you may include them # in the list passed to sess.run() and the value tensors will be # returned in the tuple from the call. _, loss_value = sess.run([train_op, loss], feed_dict = feed_dict) duration = time.time() - start_time # Write the summaries and print an overview fairly often. if step % 100 == 0: # Print status to stdout. print('Step %d: loss = %.2f (%.3f sec)' % (s ce7d tep, loss_value, duration)) # Update the events file. summary_str = sess.run(summary, feed_dict=feed_dict) summary_writer.add_summary(summary_str, step) summary_writer.flush() # Save a checkpoint and evaluate the model periodically. if (step + 1) % 1000 == 0 or (step + 1) == FLAGS.max_steps: checkpoint_file = os.path.join(FLAGS.log_dir, 'model.ckpt') saver.save(sess, checkpoint_file, global_step=step) # Evaluate against the training set. print('Training Data Eval:') do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_sets.train) # Evaluate against the validation set. print('Validation Data Eval:') do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_sets.validation) # Evaluate against the test set. print('Test Data Eval:') do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_sets.test) def main(_): if tf.gfile.Exists(FLAGS.log_dir): tf.gfile.DeleteRecursively(FLAGS.log_dir) tf.gfile.MakeDirs(FLAGS.log_dir) run_training() if __name__ == '__main__': parser = argparse.ArgumentParser() parser.add_argument( '--learning_rate', type=float, default=0.01, help='Initial learning rate.' ) parser.add_argument( '--max_steps', type=int, default=2000, help='Number of steps to run trainer.' ) parser.add_argument( '--hidden1', type=int, default=128, help='Number of units in hidden layer 1.' ) parser.add_argument( '--hidden2', type=int, default=32, help='Number of units in hidden layer 2.' ) parser.add_argument( '--batch_size', type=int, default=100, help='Batch size. Must divide evenly into the dataset sizes.' ) parser.add_argument( '--input_data_dir', type=str, default=os.path.join(os.getenv('TEST_TMPDIR', '/tmp'), 'tensorflow/mnist/input_data'), help='Directory to put the input data.' ) parser.add_argument( '--log_dir', type=str, default=os.path.join(os.getenv('TEST_TMPDIR', '/tmp'), 'tensorflow/mnist/logs/fully_connected_feed'), help='Directory to put the log data.' ) parser.add_argument( '--fake_data', default=False, help='If true, uses fake data for unit testing.', action='store_true' ) FLAGS, unparsed = parser.parse_known_args() tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
Extracting /tmp/tensorflow/mnist/input_data/train-images-idx3-ubyte.gz Extracting /tmp/tensorflow/mnist/input_data/train-labels-idx1-ubyte.gz Extracting /tmp/tensorflow/mnist/input_data/t10k-images-idx3-ubyte.gz Extracting /tmp/tensorflow/mnist/input_data/t10k-labels-idx1-ubyte.gz Step 0: loss = 2.30 (0.692 sec) Step 100: loss = 2.18 (0.001 sec) Step 200: loss = 1.91 (0.001 sec) Step 300: loss = 1.57 (0.002 sec) Step 400: loss = 1.34 (0.001 sec) Step 500: loss = 0.89 (0.001 sec) Step 600: loss = 0.83 (0.001 sec) Step 700: loss = 0.60 (0.001 sec) Step 800: loss = 0.59 (0.002 sec) Step 900: loss = 0.61 (0.002 sec) Training Data Eval: Num examples: 55000 Num correct: 47490 Precision @ 1: 0.8635 Validation Data Eval: Num examples: 5000 Num correct: 4362 Precision @ 1: 0.8724 Test Data Eval: Num examples: 10000 Num correct: 8719 Precision @ 1: 0.8719 Step 1000: loss = 0.53 (0.014 sec) Step 1100: loss = 0.43 (15.238 sec) Step 1200: loss = 0.50 (0.001 sec) Step 1300: loss = 0.39 (0.001 sec) Step 1400: loss = 0.41 (0.002 sec) Step 1500: loss = 0.42 (0.002 sec) Step 1600: loss = 0.43 (0.002 sec) Step 1700: loss = 0.45 (0.001 sec) Step 1800: loss = 0.42 (0.001 sec) Step 1900: loss = 0.38 (0.001 sec) Training Data Eval: Num examples: 55000 Num correct: 49328 Precision @ 1: 0.8969 Validation Data Eval: Num examples: 5000 Num correct: 4534 Precision @ 1: 0.9068 Test Data Eval: Num examples: 10000 Num correct: 9016 Precision @ 1: 0.9016
相关文章推荐
- TensorFlow Mechanics 101解读
- TensorFlow官方教程学习 TensorFlow Mechanics 101
- tensorflow学习(2)TensorFlow Mechanics 101
- tensorflow学习笔记十三:TF官方教程学习 TensorFlow Mechanics 101
- TensorsFlow学习笔记5----TensorFlow Mechanics 101基本运作方式
- TensorFlow官方教程学习 TensorFlow Mechanics 101
- tensorflow IOError: [Errno socket error] [Errno 101] Network is unreachable
- Tensorflow + ResNet101 + fasterRcnn 训练自己的模型 数据(一)
- TensorFlow源码阅读——tensorflow/examples/tutorials/minist目录
- TensorFlowOnSpark 初体验
- TensorFlow install
- Machine Learning with Scikit-Learn and Tensorflow 6.9 决策树局限性
- Ubuntu16.04 +cuda8.0+cudnn+opencv3.1.0+tensorflow+torch配置明细
- Machine Learning with Scikit-Learn and Tensorflow 7 集成学习和随机森林(章节目录)
- 学习笔记:SAE TensorFlow代码
- TensorFlow VGG-16 预训练模型
- Amazon AWS上Tensorflow+GPU+CUDA 8+cuDNN 5+OpenBLAS配置
- win7安装Anaconda+TensorFlow+配置PyCharm
- Notes on Tensorflow(四)Variables
- TensorFlow. tf.reduce_mean