tensorflow实战——tensorflow实现AlexNet

#%%
# 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.
# ==============================================================================
from datetime import datetime
import math
import time
import tensorflow as tf


batch_size=32
num_batches=100

#一个用来显示每一层jiego
def print_activations(t):
    #接受一个tensor作为输入，显示其名称和tensor尺寸
    print(t.op.name, ' ', t.get_shape().as_list())


def inference(images):
    parameters = []
    # conv1
    #通过这种写法可以将scope内生成的Variable自动命名为c
    #onv1/xxx,便于区分不同卷积层之间的组件
    with tf.name_scope('conv1') as scope:
        #使用截断的正太分布函数初始化卷积核的参数kernel
        kernel = tf.Variable(tf.truncated_normal([11, 11, 3, 64], dtype=tf.float32,
                                                 stddev=1e-1), name='weights')
        conv = tf.nn.conv2d(images, kernel, [1, 4, 4, 1], padding='SAME')
        biases = tf.Variable(tf.constant(0.0, shape=[64], dtype=tf.float32),
                             trainable=True, name='biases')
        #将conv和biases加起来
        bias = tf.nn.bias_add(conv, biases)
        conv1 = tf.nn.relu(bias, name=scope)
        #打印conv1的结构
        print_activations(conv1)
        parameters += [kernel, biases]


  # pool1
  #4:depth_radius
    lrn1 = tf.nn.lrn(conv1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='lrn1')
    #第二个参数ksize：池化窗口的大小，取一个四维向量，一般是[1, height, width, 1]，
    #因为我们不想在batch和channels上做池化，所以这两个维度设为了1
    pool1 = tf.nn.max_pool(lrn1,
                           ksize=[1, 3, 3, 1],
                           strides=[1, 2, 2, 1],
                           padding='VALID',
                           name='pool1')
    print_activations(pool1)

  # conv2
    with tf.name_scope('conv2') as scope:
        #输入通道数急死上一层的卷积核数量
        kernel = tf.Variable(tf.truncated_normal([5, 5, 64, 192], dtype=tf.float32,
                                                 stddev=1e-1), name='weights')
        #卷积的步长全部设为1
        conv = tf.nn.conv2d(pool1, kernel, [1, 1, 1, 1], padding='SAME')
        biases = tf.Variable(tf.constant(0.0, shape=[192], dtype=tf.float32),
                             trainable=True, name='biases')
        bias = tf.nn.bias_add(conv, biases)
        conv2 = tf.nn.relu(bias, name=scope)
        parameters += [kernel, biases]
    print_activations(conv2)

  # pool2
    lrn2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='lrn2')
    pool2 = tf.nn.max_pool(lrn2,
                           ksize=[1, 3, 3, 1],
                           strides=[1, 2, 2, 1],
                           padding='VALID',
                           name='pool2')
    print_activations(pool2)

  # conv3
    with tf.name_scope('conv3') as scope:
        kernel = tf.Variable(tf.truncated_normal([3, 3, 192, 384],
                                                 dtype=tf.float32,
                                                 stddev=1e-1), name='weights')
        conv = tf.nn.conv2d(pool2, kernel, [1, 1, 1, 1], padding='SAME')
        biases = tf.Variable(tf.constant(0.0, shape=[384], dtype=tf.float32),
                             trainable=True, name='biases')
        bias = tf.nn.bias_add(conv, biases)
        conv3 = tf.nn.relu(bias, name=scope)
        parameters += [kernel, biases]
        print_activations(conv3)

  # conv4
    with tf.name_scope('conv4') as scope:
        kernel = tf.Variable(tf.truncated_normal([3, 3, 384, 256],
                                                 dtype=tf.float32,
                                                 stddev=1e-1), name='weights')
        conv = tf.nn.conv2d(conv3, kernel, [1, 1, 1, 1], padding='SAME')
        biases = tf.Variable(tf.constant(0.0, shape=[256], dtype=tf.float32),
                             trainable=True, name='biases')
        bias = tf.nn.bias_add(conv, biases)
        conv4 = tf.nn.relu(bias, name=scope)
        parameters += [kernel, biases]
        print_activations(conv4)

  # conv5
    with tf.name_scope('conv5') as scope:
        kernel = tf.Variable(tf.truncated_normal([3, 3, 256, 256],
                                                 dtype=tf.float32,
                                                 stddev=1e-1), name='weights')
        conv = tf.nn.conv2d(conv4, kernel, [1, 1, 1, 1], padding='SAME')
        biases = tf.Variable(tf.constant(0.0, shape=[256], dtype=tf.float32),
                             trainable=True, name='biases')
        bias = tf.nn.bias_add(conv, biases)
        conv5 = tf.nn.relu(bias, name=scope)
        parameters += [kernel, biases]
        print_activations(conv5)

  # pool5
    pool5 = tf.nn.max_pool(conv5,
                           ksize=[1, 3, 3, 1],
                           strides=[1, 2, 2, 1],
                           padding='VALID',
                           name='pool5')
    print_activations(pool5)

    return pool5, parameters


def time_tensorflow_run(session, target, info_string):
#  """Run the computation to obtain the target tensor and print timing stats.
#
#  Args:
#    session: the TensorFlow session to run the computation under.
#    target: the target Tensor that is passed to the session's run() function.
#    info_string: a string summarizing this run, to be printed with the stats.
#
#  Returns:
#    None
#  """
    num_steps_burn_in = 10
    total_duration = 0.0
    total_duration_squared = 0.0
    for i in range(num_batches + num_steps_burn_in):
        start_time = time.time()
        _ = session.run(target)
        duration = time.time() - start_time
        if i >= num_steps_burn_in:
            if not i % 10:
                print ('%s: step %d, duration = %.3f' %
                       (datetime.now(), i - num_steps_burn_in, duration))
            total_duration += duration
            total_duration_squared += duration * duration
            #平均耗时
    mn = total_duration / num_batches
    vr = total_duration_squared / num_batches - mn * mn
    #标准差
    sd = math.sqrt(vr)
    print ('%s: %s across %d steps, %.3f +/- %.3f sec / batch' %
           (datetime.now(), info_string, num_batches, mn, sd))



def run_benchmark():
#  """Run the benchmark on AlexNet."""
    #定义默认的Graph
    with tf.Graph().as_default():
    # Generate some dummy images.
        image_size = 224
    # Note that our padding definition is slightly different the cuda-convnet.
    # In order to force the model to start with the same activations sizes,
    # we add 3 to the image_size and employ VALID padding above.
        images = tf.Variable(tf.random_normal([batch_size,
                                           image_size,
                                           image_size, 3],
                                          dtype=tf.float32,
                                          stddev=1e-1))

    # Build a Graph that computes the logits predictions from the
    # inference model.
        #构建整个AlexNet网络
        pool5, parameters = inference(images)

    # Build an initialization operation.
        #初始化所有参数
        init = tf.global_variables_initializer()

    # Start running operations on the Graph.
        config = tf.ConfigProto()
        config.gpu_options.allocator_type = 'BFC'
        sess = tf.Session(config=config)
        sess.run(init)

    # Run the forward benchmark.
        time_tensorflow_run(sess, pool5, "Forward")

    # Add a simple objective so we can calculate the backward pass.
        #计算pool5的loss
        objective = tf.nn.l2_loss(pool5)
    # Compute the gradient with respect to all the parameters.
        grad = tf.gradients(objective, parameters)
    # Run the backward benchmark.
        time_tensorflow_run(sess, grad, "Forward-backward")


run_benchmark()