文|Seraph
01 | 新手入門
一、介紹
- 平面擬合代碼
import tensorflow as tf
import numpy as np
# 使用 NumPy 生成假數據(phony data), 總共 100 個點.
x_data = np.float32(np.random.rand(2, 100)) # 隨機輸入
y_data = np.dot([0.100, 0.200], x_data) + 0.300
# 構造一個線性模型
#
b = tf.Variable(tf.zeros([1]))
W = tf.Variable(tf.random_uniform([1, 2], -1.0, 1.0))
y = tf.matmul(W, x_data) + b
# 最小化方差
loss = tf.reduce_mean(tf.square(y - y_data))
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)
# 初始化變量
init = tf.initialize_all_variables()
# 啓動圖 (graph)
sess = tf.Session()
sess.run(init)
# 擬合平面
for step in xrange(0, 201):
sess.run(train)
if step % 20 == 0:
print step, sess.run(W), sess.run(b)
# 得到最佳擬合結果 W: [[0.100 0.200]], b: [0.300]
二、安裝方式（源碼安裝，後續再看）
-
tensorflow分CPU與GPU版本。
-
安裝方式有：Pip、Docker、virtualenv、
Mac OS X：homebrew -
如要支持GPU，需要正確安裝CUDA，安裝CUDA記得設置環境變量
export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/cuda/lib64"
export CUDA_HOME=/usr/local/cuda
- 源碼安裝
git clone --recurse-submodules https://github.com/tensorflow/tensorflow克隆源碼- 安裝Bazel
三、基本用法
- 使用tensorflow必須明白的點：
- 使用圖 (graph) 來表示計算任務.
- 在被稱之爲 會話 (Session) 的上下文 (context) 中執行圖.
- 使用 tensor 表示數據.
- 通過 變量 (Variable) 維護狀態.
- 使用 feed 和 fetch 可以爲任意的操作(arbitrary operation) 賦值或者從其中獲取數據.
- 將一小組圖像集表示爲一個四維浮點數數組, 這四個維度分別是 [batch, height, width, channels]。
- 一個 TensorFlow 圖描述了計算的過程. 爲了進行計算, 圖必須在 會話 裏被啓動. 會話 將圖的 op 分發到諸如 CPU 或 GPU 之類的 設備 上, 同時提供執行 op 的方法.
- 如果檢測到 GPU, TensorFlow 會盡可能地利用找到的第一個 GPU 來執行操作.
如果機器上有超過一個可用的 GPU, 除第一個外的其它 GPU 默認是不參與計算的. 爲了讓 TensorFlow 使用這些 GPU, 你必須將 op 明確指派給它們執行.（需要注意的是GPU需要CUDA工具的支持，否則tensorflow檢測不到GPU，依然會默認使用CPU進行計算） - 爲了便於使用諸如 IPython 之類的 Python 交互環境, 可以使用 InteractiveSession 代替 Session 類，使用Tensor.eval()和Operation.run()代替Session.run()。
- Rank表示階，Shape表示形狀，Type表示類型。
- 用列表的形式可以取出多個結果：
result = sess.run([mul, intermed])。 - Feed機制：提供 feed 數據作爲 run() 調用的參數. feed 只在調用它的方法內有效, 方法結束, feed 就會消失。
02 | 完整教程
一、MNIST入門
- 把這個數組展開成一個向量，長度是 28x28 = 784，展平圖片的數字數組會丟失圖片的二維結構信息。這顯然是不理想的，最優秀的計算機視覺方法會挖掘並利用這些結構信息。
- mnist.train.images 是一個形狀爲 [60000, 784] 的張量
- mnist.train.labels 是一個 [60000, 10]
- 爲了用python實現高效的數值計算，我們通常會使用函數庫，比如NumPy，會把類似矩陣乘法這樣的複雜運算使用其他外部語言實現。不幸的是，從外部計算切換回Python的每一個操作，仍然是一個很大的開銷。如果你用GPU來進行外部計算，這樣的開銷會更大。用分佈式的計算方式，也會花費更多的資源用來傳輸數據。
TensorFlow也把複雜的計算放在python之外完成，但是爲了避免前面說的那些開銷，它做了進一步完善。Tensorflow不單獨地運行單一的複雜計算，而是讓我們可以先用圖描述一系列可交互的計算操作，然後全部一起在Python之外運行。 - 使用一小部分的隨機數據來進行訓練被稱爲隨機訓練（stochastic training）- 在這裏更確切的說是隨機梯度下降訓練。在理想情況下，我們希望用我們所有的數據來進行每一步的訓練，因爲這能給我們更好的訓練結果，但顯然這需要很大的計算開銷。所以，每一次訓練我們可以使用不同的數據子集，這樣做既可以減少計算開銷，又可以最大化地學習到數據集的總體特性。
import tensorflow as tf
old_v = tf.logging.get_verbosity()
tf.logging.set_verbosity(tf.logging.ERROR)
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
tf.logging.set_verbosity(old_v)
x = tf.placeholder("float", [None, 784])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x,W) + b)
y_ = tf.placeholder("float", [None,10])
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_:batch_ys})
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
二、MNIST進階
使用卷積神經網絡構建模型：
import tensorflow as tf
old_v = tf.logging.get_verbosity()
tf.logging.set_verbosity(tf.logging.ERROR)
from tensorflow.examples.tutorials.mnist import input_data
sess = tf.InteractiveSession()
def weight_variable(shape): #權重在初始化時應該加入少量的噪聲來打破對稱性以及避免0梯度。
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
tf.logging.set_verbosity(old_v)
x = tf.placeholder("float", [None, 784])
y_ = tf.placeholder("float", shape=[None, 10])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
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 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)#爲了減少過擬合，我們在輸出層之前加入dropout。
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess.run(tf.initialize_all_variables())
for i in range(20000):
batch = mnist.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={
x:batch[0], y_: batch[1], keep_prob: 1.0})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})#在feed_dict中加入額外的參數keep_prob來控制dropout比例。
print("test accuracy %g"%accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
三、Tensorflow運行方式
mnist.py
"""Builds the MNIST network.
Implements the inference/loss/training pattern for model building.
1. inference() - Builds the model as far as required for running the network
forward to make predictions.
2. loss() - Adds to the inference model the layers required to generate loss.
3. training() - Adds to the loss model the Ops required to generate and
apply gradients.
This file is used by the various "fully_connected_*.py" files and not meant to
be run.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import math
import tensorflow as tf
# The MNIST dataset has 10 classes, representing the digits 0 through 9.
NUM_CLASSES = 10
# The MNIST images are always 28x28 pixels.
IMAGE_SIZE = 28
IMAGE_PIXELS = IMAGE_SIZE * IMAGE_SIZE
def inference(images, hidden1_units, hidden2_units):
"""Build the MNIST model up to where it may be used for inference.
Args:
images: Images placeholder, from inputs().
hidden1_units: Size of the first hidden layer.
hidden2_units: Size of the second hidden layer.
Returns:
softmax_linear: Output tensor with the computed logits.
"""
# Hidden 1
with tf.compat.v1.name_scope('hidden1'):
weights = tf.Variable(
tf.random.truncated_normal(
[IMAGE_PIXELS, hidden1_units],
stddev=1.0 / math.sqrt(float(IMAGE_PIXELS))), name='weights')
biases = tf.Variable(tf.zeros([hidden1_units]),
name='biases')
hidden1 = tf.nn.relu(tf.matmul(images, weights) + biases)
# Hidden 2
with tf.compat.v1.name_scope('hidden2'):
weights = tf.Variable(
tf.random.truncated_normal(
[hidden1_units, hidden2_units],
stddev=1.0 / math.sqrt(float(hidden1_units))), name='weights')
biases = tf.Variable(tf.zeros([hidden2_units]),
name='biases')
hidden2 = tf.nn.relu(tf.matmul(hidden1, weights) + biases)
# Linear
with tf.compat.v1.name_scope('softmax_linear'):
weights = tf.Variable(
tf.random.truncated_normal(
[hidden2_units, NUM_CLASSES],
stddev=1.0 / math.sqrt(float(hidden2_units))), name='weights')
biases = tf.Variable(tf.zeros([NUM_CLASSES]),
name='biases')
logits = tf.matmul(hidden2, weights) + biases
return logits
def loss(logits, labels):
"""Calculates the loss from the logits and the labels.
Args:
logits: Logits tensor, float - [batch_size, NUM_CLASSES].
labels: Labels tensor, int32 - [batch_size].
Returns:
loss: Loss tensor of type float.
"""
labels = tf.cast(labels, dtype=tf.int64)
return tf.compat.v1.losses.sparse_softmax_cross_entropy(
labels=labels, logits=logits)
def training(loss, learning_rate):
"""Sets up the training Ops.
Creates a summarizer to track the loss over time in TensorBoard.
Creates an optimizer and applies the gradients to all trainable variables.
The Op returned by this function is what must be passed to the
`sess.run()` call to cause the model to train.
Args:
loss: Loss tensor, from loss().
learning_rate: The learning rate to use for gradient descent.
Returns:
train_op: The Op for training.
"""
# Add a scalar summary for the snapshot loss.
tf.compat.v1.summary.scalar('loss', loss)
# Create the gradient descent optimizer with the given learning rate.
optimizer = tf.compat.v1.train.GradientDescentOptimizer(learning_rate)
# Create a variable to track the global step.
global_step = tf.Variable(0, name='global_step', trainable=False)
# Use the optimizer to apply the gradients that minimize the loss
# (and also increment the global step counter) as a single training step.
train_op = optimizer.minimize(loss, global_step=global_step)
return train_op
def evaluation(logits, labels):
"""Evaluate the quality of the logits at predicting the label.
Args:
logits: Logits tensor, float - [batch_size, NUM_CLASSES].
labels: Labels tensor, int32 - [batch_size], with values in the
range [0, NUM_CLASSES).
Returns:
A scalar int32 tensor with the number of examples (out of batch_size)
that were predicted correctly.
"""
# For a classifier model, we can use the in_top_k Op.
# It returns a bool tensor with shape [batch_size] that is true for
# the examples where the label is in the top k (here k=1)
# of all logits for that example.
correct = tf.nn.in_top_k(predictions=logits, targets=labels, k=1)
# Return the number of true entries.
return tf.reduce_sum(input_tensor=tf.cast(correct, tf.int32))
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.
# ==============================================================================
"""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
ld_v = tf.logging.get_verbosity()
tf.logging.set_verbosity(tf.logging.ERROR)
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.compat.v1.placeholder(
tf.float32, shape=(batch_size, mnist.IMAGE_PIXELS))
labels_placeholder = tf.compat.v1.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.compat.v1.summary.merge_all()
# Add the variable initializer Op.
init = tf.compat.v1.global_variables_initializer()
# Create a saver for writing training checkpoints.
saver = tf.compat.v1.train.Saver()
# Create a session for running Ops on the Graph.
sess = tf.compat.v1.Session()
# Instantiate a SummaryWriter to output summaries and the Graph.
summary_writer = tf.compat.v1.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)' % (step, 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.io.gfile.exists(FLAGS.log_dir):
tf.io.gfile.rmtree(FLAGS.log_dir)
tf.io.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.compat.v1.app.run(main=main, argv=[sys.argv[0]] + unparsed)