# 《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:sz06.02.py # TensorFlow实现VGGNet
# 参考 https://github.com/machrisaa/tensorflow-vgg
from datetime import datetime
import math
import time
import tensorflow as tf
def conv_op(input_op, name, kh, kw, n_out, dh, dw, p):
n_in = input_op.get_shape()[-1].value
with tf.name_scope(name) as scope:
kernel = tf.get_variable(scope + "w",
shape = [kh, kw, n_in, n_out], dtype=tf.float32,
initializer = tf.contrib.layers.xavier_initializer_conv2d())
conv = tf.nn.conv2d(input_op, kernel, (1, dh, dw, 1), padding='SAME')
bias_init_val = tf.constant(0.0, shape=[n_out], dtype=tf.float32)
biases = tf.Variable(bias_init_val, trainable=True, name='b')
z = tf.nn.bias_add(conv, biases)
activation = tf.nn.relu(z, name=scope)
p += [kernel, biases]
return activation
def fc_op(input_op, name, n_out, p):
n_in = input_op.get_shape()[-1].value
with tf.name_scope(name) as scope:
kernel = tf.get_variable(scope + "w",
shape=[n_in, n_out], dtype=tf.float32,
initializer=tf.contrib.layers.xavier_initializer())
biases = tf.Variable(tf.constant(0.1, shape=[n_out], dtype=tf.float32), name='b')
activation = tf.nn.relu_layer(input_op, kernel, biases, name=scope)
p += [kernel, biases]
return activation
def mpool_op(input_op, name, kh, kw, dh, dw):
return tf.nn.max_pool(input_op,
ksize=[1, kh, kw, 1],
strides=[1, dh, dw, 1],
padding='SAME',
name=name)
def inference_op(input_op, keep_prob):
p = []
conv1_1 = conv_op(input_op, name="conv1_1", kh=3, kw=3, n_out=64, dh=1, dw=1, p=p)
conv1_2 = conv_op(conv1_1, name="conv1_2", kh=3, kw=3, n_out=64, dh=1, dw=1, p=p)
pool1 = mpool_op(conv1_2, name="pool1", kh=2, kw=2, dh=2, dw=2)
conv2_1 = conv_op(pool1, name="conv2_1", kh=3, kw=3, n_out=128, dh=1, dw=1, p=p)
conv2_2 = conv_op(conv2_1, name="conv2_2", kh=3, kw=3, n_out=128, dh=1, dw=1, p=p)
pool2 = mpool_op(conv2_2, name="pool2", kh=2, kw=2, dh=2, dw=2)
conv3_1 = conv_op(pool2, name="conv3_1", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
conv3_2 = conv_op(conv3_1, name="conv3_2", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
conv3_3 = conv_op(conv3_2, name="conv3_3", kh=3, kw=3, n_out=256, dh=1,dw=1, p=p)
pool3 = mpool_op(conv3_3, name="pool3", kh=2, kw=2, dh=2, dw=2)
conv4_1 = conv_op(pool3, name="conv4_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv4_2 = conv_op(conv4_1, name="conv4_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv4_3 = conv_op(conv4_2, name="conv4_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
pool4 = mpool_op(conv4_3, name="pool4", kh=2, kw=2, dh=2, dw=2)
conv5_1 = conv_op(pool4, name="conv5_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv5_2 = conv_op(conv5_1, name="conv5_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv5_3 = conv_op(conv5_2, name="conv5_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
pool5 = mpool_op(conv5_3, name="pool5", kh=2, kw=2, dh=2, dw=2)
shp = pool5.get_shape()
flattened_shape = shp[1].value * shp[2].value * shp[3].value
resh1 = tf.reshape(pool5, [-1, flattened_shape], name="resh1")
fc6 = fc_op(resh1, name="fc6", n_out=4096, p=p)
fc6_drop = tf.nn.dropout(fc6, keep_prob, name="fc6_drop")
fc7 = fc_op(fc6_drop, name="fc7", n_out=4096, p=p)
fc7_drop = tf.nn.dropout(fc7, keep_prob, name="fc7_drop")
fc8 = fc_op(fc7_drop, name="fc8", n_out=1000, p=p)
softmax = tf.nn.softmax(fc8)
predictions = tf.argmax(softmax, 1)
return predictions, softmax, fc8, p
def time_tensorflow_run(session, target, feed, 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, feed_dict=feed)
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():
images_size = 224
images = tf.Variable(tf.random_normal([batch_size, images_size, images_size, 3],
dtype = tf.float32,
stddev = 1e-1))
keep_prob = tf.placeholder(tf.float32)
predictions, softmax, fc8, p = inference_op(images, keep_prob)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
time_tensorflow_run(sess, predictions, {keep_prob: 1.0}, "Forward")
objective = tf.nn.l2_loss(fc8)
grad = tf.gradients(objective, p)
time_tensorflow_run(sess, grad, {keep_prob: 0.5}, "Forward-backward")
batch_size = 32
num_batches = 100
run_benchmark()
'''
2017-04-13 20:46:38.301421: step 0, duration = 0.876
2017-04-13 20:46:47.062714: step 10, duration = 0.876
2017-04-13 20:46:55.825010: step 20, duration = 0.876
2017-04-13 20:47:04.586824: step 30, duration = 0.876
2017-04-13 20:47:13.350110: step 40, duration = 0.876
2017-04-13 20:47:22.112488: step 50, duration = 0.876
2017-04-13 20:47:30.879796: step 60, duration = 0.876
2017-04-13 20:47:39.645100: step 70, duration = 0.877
2017-04-13 20:47:48.409402: step 80, duration = 0.876
2017-04-13 20:47:57.172700: step 90, duration = 0.876
2017-04-13 20:48:05.061676: Forward across 100 steps, 0.876 +/- 0.000 sec / batch
2017-04-13 20:48:48.393882: step 0, duration = 3.434
2017-04-13 20:49:22.706495: step 10, duration = 3.412
2017-04-13 20:49:57.018747: step 20, duration = 3.432
2017-04-13 20:50:31.359640: step 30, duration = 3.427
2017-04-13 20:51:05.571630: step 40, duration = 3.419
2017-04-13 20:51:39.908891: step 50, duration = 3.459
2017-04-13 20:52:14.316013: step 60, duration = 3.423
2017-04-13 20:52:48.706655: step 70, duration = 3.428
2017-04-13 20:53:23.171285: step 80, duration = 3.455
2017-04-13 20:53:57.729194: step 90, duration = 3.460
2017-04-13 20:54:28.629420: Forward-backward across 100 steps, 3.437 +/- 0.020 sec / batch
'''
tensorflow34《TensorFlow实战》笔记-06-02 TensorFlow实现VGGNet code
最新推荐文章于 2022-07-17 11:03:19 发布