# 《TensorFlow实战》06 TensorFlow实现经典卷积神经网络
# win10 Tensorflow1.0.1 python3.5.3
# CUDA v8.0 cudnn-8.0-windows10-x64-v5.1
# filename:sz06.01.py # TensorFlow实现AlexNet
# 参考内容
# https://github.com/tensorflow/models/blob/master/tutorials/image/alexnet/alexnet_benchmark.py
# https://github.com/tensorflow/models.git
# tensorflow_models\tutorials\image\alexnet\alexnet_benchmark.py
from datetime import datetime
import math
import time
import tensorflow as tf
batch_size = 32
num_batches = 100
def print_activations(t):
print(t.op.name, ' ', t.get_shape().as_list())
def infrence(images):
parameters = []
with tf.name_scope('conv1') as scope:
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')
bias = tf.nn.bias_add(conv, biases)
conv1 = tf.nn.relu(bias, name = scope)
print_activations(conv1)
parameters = [kernel, biases]
lrn1 = tf.nn.lrn(conv1, 4, bias = 1.0, alpha = 0.001/9, beta = 0.75, name = 'lrn1')
pool1 = tf.nn.max_pool(lrn1, ksize = [1, 3, 3, 1], strides = [1, 2, 2, 1], padding = 'VALID', name = 'pool1')
print_activations(pool1)
with tf.name_scope('conv2') as scope:
kernel = tf.Variable(tf.truncated_normal([5, 5, 64, 192], dtype = tf.float32, stddev = 1e-1), name = 'weights')
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)
lrn2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha = 0.001/9, 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)
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)
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)
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 =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):
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
mn = total_duration / num_batches
vr = total_duration_squared / num_batches - mn * mn
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():
with tf.Graph().as_default():
image_size = 224
images = tf.Variable(tf.random_normal([batch_size, image_size, image_size, 3], dtype = tf.float32, stddev = 1e-1))
pool5, parameters = infrence(images)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
time_tensorflow_run(sess, pool5, "Forward")
objective = tf.nn.l2_loss(pool5)
grad = tf.gradients(objective, parameters)
time_tensorflow_run(sess, grad, "Forward-backward")
run_benchmark()
'''
conv1 [32, 56, 56, 64]
pool1 [32, 27, 27, 64]
conv2 [32, 27, 27, 192]
pool2 [32, 13, 13, 192]
conv3 [32, 13, 13, 384]
conv4 [32, 13, 13, 256]
conv5 [32, 13, 13, 256]
pool5 [32, 6, 6, 256]
2017-04-13 16:28:25.177867: step 0, duration = 0.059
2017-04-13 16:28:25.769441: step 10, duration = 0.059
2017-04-13 16:28:26.361012: step 20, duration = 0.059
2017-04-13 16:28:26.951583: step 30, duration = 0.059
2017-04-13 16:28:27.543156: step 40, duration = 0.059
2017-04-13 16:28:28.131719: step 50, duration = 0.059
2017-04-13 16:28:28.724311: step 60, duration = 0.059
2017-04-13 16:28:29.314866: step 70, duration = 0.059
2017-04-13 16:28:29.905437: step 80, duration = 0.059
2017-04-13 16:28:30.496006: step 90, duration = 0.059
2017-04-13 16:28:31.033435: Forward across 100 steps, 0.059 +/- 0.001 sec / batch
2017-04-13 16:28:33.830872: step 0, duration = 0.204
2017-04-13 16:28:35.877314: step 10, duration = 0.203
2017-04-13 16:28:37.911570: step 20, duration = 0.204
2017-04-13 16:28:39.954005: step 30, duration = 0.205
2017-04-13 16:28:41.987445: step 40, duration = 0.205
2017-04-13 16:28:44.026828: step 50, duration = 0.203
2017-04-13 16:28:46.063242: step 60, duration = 0.204
2017-04-13 16:28:48.103667: step 70, duration = 0.204
2017-04-13 16:28:50.141083: step 80, duration = 0.202
2017-04-13 16:28:52.172485: step 90, duration = 0.203
2017-04-13 16:28:54.002348: Forward-backward across 100 steps, 0.204 +/- 0.001 sec / batch
'''
tensorflow33《TensorFlow实战》笔记-06-01 TensorFlow实现AlexNet code
最新推荐文章于 2020-04-03 15:56:41 发布