MNIST 例程源码分析 TensorFlow 从入门到精通

按照上节步骤, TensorFlow 默认安装在 /usr/lib/python/site-packages/tensorflow/ (也有可能是 /usr/local/lib……)下,查看目录结构:

  1 # tree -d -L 3 /usr/lib/python2.7/site-packages/tensorflow/
  2 /usr/lib/python2.7/site-packages/tensorflow/
  3 ├── contrib
  4 │   ├── bayesflow
  5 │   │   └── python
  6 │   ├── cmake
  7 │   ├── copy_graph
  8 │   │   └── python
  9 │   ├── crf
 10 │   │   └── python
 11 │   ├── cudnn_rnn
 12 │   │   ├── ops
 13 │   │   └── python
 14 │   ├── distributions
 15 │   │   └── python
 16 │   ├── factorization
 17 │   │   └── python
 18 │   ├── ffmpeg
 19 │   │   └── ops
 20 │   ├── framework
 21 │   │   └── python
 22 │   ├── graph_editor
 23 │   ├── grid_rnn
 24 │   │   └── python
 25 │   ├── layers
 26 │   │   ├── ops
 27 │   │   └── python
 28 │   ├── learn
 29 │   │   └── python
 30 │   ├── linear_optimizer
 31 │   │   ├── ops
 32 │   │   └── python
 33 │   ├── lookup
 34 │   ├── losses
 35 │   │   └── python
 36 │   ├── metrics
 37 │   │   ├── ops
 38 │   │   └── python
 39 │   ├── opt
 40 │   │   └── python
 41 │   ├── quantization
 42 │   │   ├── kernels
 43 │   │   ├── ops
 44 │   │   └── python
 45 │   ├── rnn
 46 │   │   └── python
 47 │   ├── session_bundle
 48 │   ├── slim
 49 │   │   └── python
 50 │   ├── tensorboard
 51 │   │   └── plugins
 52 │   ├── tensor_forest
 53 │   │   ├── client
 54 │   │   ├── data
 55 │   │   ├── hybrid
 56 │   │   └── python
 57 │   ├── testing
 58 │   │   └── python
 59 │   ├── training
 60 │   │   └── python
 61 │   └── util
 62 ├── core
 63 │   ├── example
 64 │   ├── framework
 65 │   ├── lib
 66 │   │   └── core
 67 │   ├── protobuf
 68 │   └── util
 69 ├── examples
 70 │   └── tutorials
 71 │       └── mnist
 72 ├── include
 73 │   ├── Eigen
 74 │   │   └── src
 75 │   ├── external
 76 │   │   └── eigen_archive
 77 │   ├── google
 78 │   │   └── protobuf
 79 │   ├── tensorflow
 80 │   │   └── core
 81 │   ├── third_party
 82 │   │   └── eigen3
 83 │   └── unsupported
 84 │       └── Eigen
 85 ├── models
 86 │   ├── embedding
 87 │   ├── image
 88 │   │   ├── alexnet
 89 │   │   ├── cifar10
 90 │   │   ├── imagenet
 91 │   │   └── mnist
 92 │   └── rnn
 93 │       ├── ptb
 94 │       └── translate
 95 ├── python
 96 │   ├── client
 97 │   ├── debug
 98 │   │   └── cli
 99 │   ├── framework
100 │   ├── lib
101 │   │   ├── core
102 │   │   └── io
103 │   ├── ops
104 │   ├── platform
105 │   ├── saved_model
106 │   ├── summary
107 │   │   └── impl
108 │   ├── training
109 │   ├── user_ops
110 │   └── util
111 │       └── protobuf
112 ├── tensorboard
113 │   ├── backend
114 │   ├── dist
115 │   ├── lib
116 │   │   ├── css
117 │   │   └── python
118 │   └── plugins
119 │       └── projector
120 └── tools
121     └── pip_package
122 
123 119 directories

上节运行 MNIST 例程的命令为:

# python -m tensorflow.models.image.mnist.convolutional
对应文件为 /usr/lib/python2.7/site-packages/tensorflow/models/image/mnist/convolutional.py

打开例程源码:

  1 # Copyright 2015 Google Inc. All Rights Reserved.
  2 #
  3 # Licensed under the Apache License, Version 2.0 (the "License");
  4 # you may not use this file except in compliance with the License.
  5 # You may obtain a copy of the License at
  6 #
  7 #     http://www.apache.org/licenses/LICENSE-2.0
  8 #
  9 # Unless required by applicable law or agreed to in writing, software
 10 # distributed under the License is distributed on an "AS IS" BASIS,
 11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 12 # See the License for the specific language governing permissions and
 13 # limitations under the License.
 14 # ==============================================================================
 15 
 16 """Simple, end-to-end, LeNet-5-like convolutional MNIST model example.
 17 
 18 This should achieve a test error of 0.7%. Please keep this model as simple and
 19 linear as possible, it is meant as a tutorial for simple convolutional models.
 20 Run with --self_test on the command line to execute a short self-test.
 21 """
 22 from __future__ import absolute_import
 23 from __future__ import division
 24 from __future__ import print_function
 25 
 26 import gzip
 27 import os
 28 import sys
 29 import time
 30 
 31 import numpy
 32 from six.moves import urllib
 33 from six.moves import xrange  # pylint: disable=redefined-builtin
 34 import tensorflow as tf
 35 
 36 # 数据源
 37 SOURCE_URL = 'http://yann.lecun.com/exdb/mnist/'
 38 # 工作目录,存放下载的数据
 39 WORK_DIRECTORY = 'data'
 40 # MNIST 数据集特征: 
 41 #     图像尺寸 28x28 
 42 IMAGE_SIZE = 28
 43 #     黑白图像
 44 NUM_CHANNELS = 1
 45 #     像素值0~255 
 46 PIXEL_DEPTH = 255
 47 #     标签分10个类别
 48 NUM_LABELS = 10
 49 #     验证集共 5000 个样本
 50 VALIDATION_SIZE = 5000  
 51 # 随机数种子,可设为 None 表示真的随机
 52 SEED = 66478 
 53 # 批处理大小为64
 54 BATCH_SIZE = 64
 55 # 数据全集一共过10遍网络
 56 NUM_EPOCHS = 10
 57 # 验证集批处理大小也是64
 58 EVAL_BATCH_SIZE = 64
 59 # 验证时间间隔,每训练100个批处理,做一次评估
 60 EVAL_FREQUENCY = 100  
 61 
 62 
 63 tf.app.flags.DEFINE_boolean("self_test", False, "True if running a self test.")
 64 FLAGS = tf.app.flags.FLAGS
 65 
 66 # 如果下载过了数据,就不再重复下载
 67 def maybe_download(filename):
 68   """Download the data from Yann's website, unless it's already here."""
 69   if not tf.gfile.Exists(WORK_DIRECTORY):
 70     tf.gfile.MakeDirs(WORK_DIRECTORY)
 71   filepath = os.path.join(WORK_DIRECTORY, filename)
 72   if not tf.gfile.Exists(filepath):
 73     filepath, _ = urllib.request.urlretrieve(SOURCE_URL + filename, filepath)
 74     with tf.gfile.GFile(filepath) as f:
 75       size = f.Size()
 76     print('Successfully downloaded', filename, size, 'bytes.')
 77   return filepath
 78 
 79 # 抽取数据,变为 4维张量[图像索引,y, x, c]
 80 # 去均值、做归一化,范围变到[-0.5, 0.5]
 81 def extract_data(filename, num_images):
 82   """Extract the images into a 4D tensor [image index, y, x, channels].
 83 
 84   Values are rescaled from [0, 255] down to [-0.5, 0.5].
 85   """
 86   print('Extracting', filename)
 87   with gzip.open(filename) as bytestream:
 88     bytestream.read(16)
 89     buf = bytestream.read(IMAGE_SIZE * IMAGE_SIZE * num_images)
 90     data = numpy.frombuffer(buf, dtype=numpy.uint8).astype(numpy.float32)
 91     data = (data - (PIXEL_DEPTH / 2.0)) / PIXEL_DEPTH
 92     data = data.reshape(num_images, IMAGE_SIZE, IMAGE_SIZE, 1)
 93 return data
 94 
 95 # 抽取图像标签
 96 def extract_labels(filename, num_images):
 97   """Extract the labels into a vector of int64 label IDs."""
 98   print('Extracting', filename)
 99   with gzip.open(filename) as bytestream:
100     bytestream.read(8)
101     buf = bytestream.read(1 * num_images)
102     labels = numpy.frombuffer(buf, dtype=numpy.uint8).astype(numpy.int64)
103   return labels
104 
105 # 假数据,用于功能自测
106 def fake_data(num_images):
107   """Generate a fake dataset that matches the dimensions of MNIST."""
108   data = numpy.ndarray(
109       shape=(num_images, IMAGE_SIZE, IMAGE_SIZE, NUM_CHANNELS),
110       dtype=numpy.float32)
111   labels = numpy.zeros(shape=(num_images,), dtype=numpy.int64)
112   for image in xrange(num_images):
113     label = image % 2
114     data[image, :, :, 0] = label - 0.5
115     labels[image] = label
116   return data, labels
117 # 计算分类错误率
118 def error_rate(predictions, labels):
119   """Return the error rate based on dense predictions and sparse labels."""
120   return 100.0 - (
121       100.0 *
122       numpy.sum(numpy.argmax(predictions, 1) == labels) /
123 predictions.shape[0])
124 
125 
126 
127 
128 # 主函数
129 def main(argv=None):  # pylint: disable=unused-argument
130   if FLAGS.self_test:
131     print('Running self-test.')
132     train_data, train_labels = fake_data(256)
133     validation_data, validation_labels = fake_data(EVAL_BATCH_SIZE)
134     test_data, test_labels = fake_data(EVAL_BATCH_SIZE)
135     num_epochs = 1
136   else:
137     # 下载数据
138     train_data_filename = maybe_download('train-images-idx3-ubyte.gz')
139     train_labels_filename = maybe_download('train-labels-idx1-ubyte.gz')
140     test_data_filename = maybe_download('t10k-images-idx3-ubyte.gz')
141     test_labels_filename = maybe_download('t10k-labels-idx1-ubyte.gz')
142 
143     # 载入数据到numpy
144     train_data = extract_data(train_data_filename, 60000)
145     train_labels = extract_labels(train_labels_filename, 60000)
146     test_data = extract_data(test_data_filename, 10000)
147     test_labels = extract_labels(test_labels_filename, 10000)
148 
149     # 产生评测集
150     validation_data = train_data[:VALIDATION_SIZE, ...]
151     validation_labels = train_labels[:VALIDATION_SIZE]
152     train_data = train_data[VALIDATION_SIZE:, ...]
153     train_labels = train_labels[VALIDATION_SIZE:]
154     num_epochs = NUM_EPOCHS
155   train_size = train_labels.shape[0]
156 
157 # 训练样本和标签将从这里送入网络。
158 # 每训练迭代步,占位符节点将被送入一个批处理数据
159 # 训练数据节点
160   train_data_node = tf.placeholder(
161       tf.float32,
162 shape=(BATCH_SIZE, IMAGE_SIZE, IMAGE_SIZE, NUM_CHANNELS))
163 # 训练标签节点
164   train_labels_node = tf.placeholder(tf.int64, shape=(BATCH_SIZE,))
165 # 评测数据节点
166   eval_data = tf.placeholder(
167       tf.float32,
168       shape=(EVAL_BATCH_SIZE, IMAGE_SIZE, IMAGE_SIZE, NUM_CHANNELS))
169 
170 # 下面这些变量是网络的可训练权值
171 # conv1 权值维度为 32 x channels x 5 x 5, 32 为特征图数目
172   conv1_weights = tf.Variable(
173       tf.truncated_normal([5, 5, NUM_CHANNELS, 32],  # 5x5 filter, depth 32.
174                           stddev=0.1,
175                           seed=SEED))
176 # conv1 偏置
177   conv1_biases = tf.Variable(tf.zeros([32]))
178 # conv2 权值维度为 64 x 32 x 5 x 5 
179   conv2_weights = tf.Variable(
180       tf.truncated_normal([5, 5, 32, 64],
181                           stddev=0.1,
182                           seed=SEED))
183   conv2_biases = tf.Variable(tf.constant(0.1, shape=[64]))
184 # 全连接层 fc1 权值,神经元数目为512
185   fc1_weights = tf.Variable(  # fully connected, depth 512.
186       tf.truncated_normal(
187           [IMAGE_SIZE // 4 * IMAGE_SIZE // 4 * 64, 512],
188           stddev=0.1,
189           seed=SEED))
190   fc1_biases = tf.Variable(tf.constant(0.1, shape=[512]))
191 # fc2 权值,维度与标签类数目一致
192   fc2_weights = tf.Variable(
193       tf.truncated_normal([512, NUM_LABELS],
194                           stddev=0.1,
195                           seed=SEED))
196   fc2_biases = tf.Variable(tf.constant(0.1, shape=[NUM_LABELS]))
197 
198 # 两个网络:训练网络和评测网络
199 # 它们共享权值
200 
201 # 实现 LeNet-5 模型,该函数输入为数据,输出为fc2的响应
202 # 第二个参数区分训练网络还是评测网络
203   def model(data, train=False):
204 """The Model definition."""
205 # 二维卷积,使用“不变形”补零(即输出特征图与输入尺寸一致)。
206     conv = tf.nn.conv2d(data,
207                         conv1_weights,
208                         strides=[1, 1, 1, 1],
209                         padding='SAME')
210     # 加偏置、过激活函数一块完成
211 relu = tf.nn.relu(tf.nn.bias_add(conv, conv1_biases))
212     # 最大值下采样
213     pool = tf.nn.max_pool(relu,
214                           ksize=[1, 2, 2, 1],
215                           strides=[1, 2, 2, 1],
216                           padding='SAME')
217     # 第二个卷积层
218     conv = tf.nn.conv2d(pool,
219                         conv2_weights,
220                         strides=[1, 1, 1, 1],
221                         padding='SAME')
222     relu = tf.nn.relu(tf.nn.bias_add(conv, conv2_biases))
223     pool = tf.nn.max_pool(relu,
224                           ksize=[1, 2, 2, 1],
225                           strides=[1, 2, 2, 1],
226                           padding='SAME')
227 # 特征图变形为2维矩阵,便于送入全连接层
228     pool_shape = pool.get_shape().as_list()
229     reshape = tf.reshape(
230         pool,
231         [pool_shape[0], pool_shape[1] * pool_shape[2] * pool_shape[3]])
232 # 全连接层,注意“+”运算自动广播偏置
233     hidden = tf.nn.relu(tf.matmul(reshape, fc1_weights) + fc1_biases)
234 # 训练阶段,增加 50% dropout;而评测阶段无需该操作
235     if train:
236       hidden = tf.nn.dropout(hidden, 0.5, seed=SEED)
237     return tf.matmul(hidden, fc2_weights) + fc2_biases
238 
239   # Training computation: logits + cross-entropy loss.
240   # 训练阶段计算: 对数+交叉熵 损失函数
241   logits = model(train_data_node, True)
242   loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(
243       logits, train_labels_node))
244 
245 
246   # 全连接层参数进行 L2 正则化
247   regularizers = (tf.nn.l2_loss(fc1_weights) + tf.nn.l2_loss(fc1_biases) +
248                   tf.nn.l2_loss(fc2_weights) + tf.nn.l2_loss(fc2_biases))
249   # 将正则项加入损失函数
250   loss += 5e-4 * regularizers
251 
252   # 优化器: 设置一个变量,每个批处理递增,控制学习速率衰减
253   batch = tf.Variable(0)
254   # 指数衰减
255   learning_rate = tf.train.exponential_decay(
256       0.01,                # 基本学习速率
257       batch * BATCH_SIZE,  # 当前批处理在数据全集中的位置
258       train_size,          # Decay step.
259       0.95,                # Decay rate.
260       staircase=True)
261   # Use simple momentum for the optimization.
262   optimizer = tf.train.MomentumOptimizer(learning_rate,
263                                          0.9).minimize(loss,
264                                                        global_step=batch)
265 
266   # 用softmax 计算训练批处理的预测概率
267   train_prediction = tf.nn.softmax(logits)
268 
269   # 用 softmax 计算评测批处理的预测概率
270   eval_prediction = tf.nn.softmax(model(eval_data))
271 
272   # Small utility function to evaluate a dataset by feeding batches of data to
273   # {eval_data} and pulling the results from {eval_predictions}.
274   # Saves memory and enables this to run on smaller GPUs.
275   def eval_in_batches(data, sess):
276     """Get all predictions for a dataset by running it in small batches."""
277     size = data.shape[0]
278     if size < EVAL_BATCH_SIZE:
279       raise ValueError("batch size for evals larger than dataset: %d" % size)
280     predictions = numpy.ndarray(shape=(size, NUM_LABELS), dtype=numpy.float32)
281     for begin in xrange(0, size, EVAL_BATCH_SIZE):
282       end = begin + EVAL_BATCH_SIZE
283       if end <= size:
284         predictions[begin:end, :] = sess.run(
285             eval_prediction,
286             feed_dict={eval_data: data[begin:end, ...]})
287       else:
288         batch_predictions = sess.run(
289             eval_prediction,
290             feed_dict={eval_data: data[-EVAL_BATCH_SIZE:, ...]})
291         predictions[begin:, :] = batch_predictions[begin - size:, :]
292     return predictions
293 
294 
295   # Create a local session to run the training.
296   start_time = time.time()
297   with tf.Session() as sess:
298     # Run all the initializers to prepare the trainable parameters.
299     tf.initialize_all_variables().run()
300     print('Initialized!')
301     # Loop through training steps.
302     for step in xrange(int(num_epochs * train_size) // BATCH_SIZE):
303       # Compute the offset of the current minibatch in the data.
304       # Note that we could use better randomization across epochs.
305       offset = (step * BATCH_SIZE) % (train_size - BATCH_SIZE)
306       batch_data = train_data[offset:(offset + BATCH_SIZE), ...]
307       batch_labels = train_labels[offset:(offset + BATCH_SIZE)]
308       # This dictionary maps the batch data (as a numpy array) to the
309       # node in the graph it should be fed to.
310       feed_dict = {train_data_node: batch_data,
311                    train_labels_node: batch_labels}
312       # Run the graph and fetch some of the nodes.
313       _, l, lr, predictions = sess.run(
314           [optimizer, loss, learning_rate, train_prediction],
315           feed_dict=feed_dict)
316       if step % EVAL_FREQUENCY == 0:
317         elapsed_time = time.time() - start_time
318         start_time = time.time()
319         print('Step %d (epoch %.2f), %.1f ms' %
320               (step, float(step) * BATCH_SIZE / train_size,
321                1000 * elapsed_time / EVAL_FREQUENCY))
322         print('Minibatch loss: %.3f, learning rate: %.6f' % (l, lr))
323         print('Minibatch error: %.1f%%' % error_rate(predictions, batch_labels))
324         print('Validation error: %.1f%%' % error_rate(
325             eval_in_batches(validation_data, sess), validation_labels))
326         sys.stdout.flush()
327     # Finally print the result!
328     test_error = error_rate(eval_in_batches(test_data, sess), test_labels)
329     print('Test error: %.1f%%' % test_error)
330     if FLAGS.self_test:
331       print('test_error', test_error)
332       assert test_error == 0.0, 'expected 0.0 test_error, got %.2f' % (
333           test_error,)
334 # 程序入口点
335 if __name__ == '__main__':
336   tf.app.run()

  如果还有问题未能得到解决,搜索887934385交流群,进入后下载资料工具安装包等。最后,感谢观看!
posted @ 2019-11-12 22:24  pypypypy  阅读(523)  评论(0编辑  收藏  举报