AlexNet 中包含了几个比较新的技术点,
也首次在CNN中成功应用了ReLU、Dropout和LRN等Trick。同时AlexNet也使用了GPU进行运算加速,作者开源了他们在GPU上训练卷积神经网络的CUDA代码。AlexNet 包含了6亿3 000万个连接,6000万个参数和65 万个 神经元,拥有5个卷积层 , 其中3个卷 积层后面连接了最 大池化层,最后还有3个全连接 层。AlexNet以显著的优势赢得了竞争激烈的ILSVRC 2012比赛,top-5的错误率降低至了16.4%,相比第二名的成绩26.2%错误率有了巨大的提升。AlexNet可以说是神经网络在低谷期后的第一次发声, 确立了深度学习(深度卷积网络)在计算机视觉的统治地位, 同时也推动了深度 学习在语音识别、 自然语言处理 、 强化学习 等领域的拓展。
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 inference(images):
parameters = []
# conv1
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]
# pool1
lrn1 = tf.nn.lrn(conv1, 4, bias=1.0, alpha=0.001 / 9.0, 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)
# conv2
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)
# 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):
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():
# """Run the benchmark on AlexNet."""
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.
pool5, parameters = inference(images)
# Build an initialization operation.
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.
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()