- 2014年,ImageNet挑战赛(ILSVRC14)中,GoogLeNet(InceptionNet v1)获得了第一名、VGG获得了第二名,这两类模型结构的共同特点是层次更深了
InceptionNet 优点
-
InceptionNet通过分支的方式增大网络的宽度和深度能够很好的提高网络的性能,避免过拟合。
- 一般来说卷积网络要提升表达能力,主要依靠增加输出通道的数量,但是带来的副作用是计算量增大和过拟合。因此InceptionNet采用分支网络堆叠在一起产生较大通道的输出。InceptionNet中产生4个网络(3个卷积和1个池化)对前一层的输出做计算,然后将不同卷积大小的输出在通道上堆叠在一起。卷积、池化后的尺寸相同,将通道相加,一方面增加了网络的宽度,另一方面同时网络中的卷积和大小也不一样,可以增加网络对不同尺度的适应性。
InceptionNet分支采用了的卷积网络,卷积的主要目的是为了减少参数,还用于修正线性激活。因为这是一个可以跨通道组织信息,提高网络的表达能力,提供更多的非线性变换。为什么可以减少参数呢?比如,上一层的输出为,经过具有256个通道的卷积层之后(stride=1,pad=2),输出数据为,其中,卷积层的参数为。而假如上一层输出先经过具有32个通道的卷积层,再经过具有256个输出的卷积层,那么输出数据仍为为,但卷积参数量已经减少为,大约减少了4倍。
InceptionNet为了避免梯度消失,网络额外增加了2个辅助的softmax用于向前传导梯度(辅助分类器)。辅助分类器是将中间某一层的输出用作分类,并按一个较小的权重(0.3)加到最终分类结果中,这样相当于做了模型融合,同时给网络增加了反向传播的梯度信号,也提供了额外的正则化,对于整个网络的训练很有裨益。而在实际测试的时候,这两个额外的softmax会被去掉。
提出并采用了 BatchNormalization(BN)。BN是一种非常有用的正则化方法,可以让卷积网络的训练速度加快很多,同时收敛后的分类准确率也可以提高很多。BN就是神经网络在训练的时候对每个Batch数据的内部进行标准化。BN在某种程度上还起到正则的作用,所以可以减小或者取消Dropout,优化网络结构。同时添加BN后,还需要对超参数做一些调整,增大学速率,加快学习速率的衰减,去除Drought,减轻正则,去除LRN,对样本进行洗牌等等。
网络最后采用了AveragePool来代替全连接层,该想法来自NIN(Network in Network),事实证明这样可以将准确率提高0.6%。但是,实际在最后还是加了一个全连接层,主要是为了方便对输出进行灵活调整。
InceptionNet将一个较大的卷积网络拆分成两个小的卷积网络(VGGNet也使用了此思想)。比如将一个 5∗5 的卷积核分成两个 3∗3 的卷积核(作用是一样),这样可以节约大量参数,加速运算并减轻过拟合,同时增加了一层非线性变换拓展了模型的表达能力。
借鉴inceptionNet的思想,实现图片的分类
- inception_net:原尺寸
- 卷积层:filters=32,kernel_size=(3,3),strides=(1, 1),padding='same',卷积后尺寸:
- 池化层: pool_size=(2,2),strides=(2, 2),padding='same', 池化后尺寸:
- inception_block: inception后的尺寸:
- inception_block: inception后的尺寸:
- 池化层: pool_size=(2,2),strides=(2, 2),padding='valid', 池化后尺寸:
- inception_block: inception后的尺寸:
- inception_block: inception后的尺寸:
- 池化层: pool_size=(2,2),strides=(2, 2),padding='valid', 池化后尺寸:
import tensorflow as tf
import os
import pickle
import numpy as np
CIFAR_DIR = "./../cifar-10-batches-py"
print (os.listdir(CIFAR_DIR))
print(tf.__version__)
def load_data(filename):
"""read data from data file."""
with open(filename, 'rb') as f:
data = pickle.load(f, encoding='ISO8859-1')
return data['data'], data['labels']
# tensorflow.Dataset.
class CifarData:
def __init__(self, filenames, need_shuffle):
all_data = []
all_labels = []
for filename in filenames:
data, labels = load_data(filename)
all_data.append(data)
all_labels.append(labels)
self._data = np.vstack(all_data)
self._data = self._data / 127.5 - 1
self._labels = np.hstack(all_labels)
print (self._data.shape)
print (self._labels.shape)
self._num_examples = self._data.shape[0]
self._need_shuffle = need_shuffle
self._indicator = 0
if self._need_shuffle:
self._shuffle_data()
def _shuffle_data(self):
# [0,1,2,3,4,5] -> [5,3,2,4,0,1]
p = np.random.permutation(self._num_examples)
self._data = self._data[p]
self._labels = self._labels[p]
def next_batch(self, batch_size):
"""return batch_size examples as a batch."""
end_indicator = self._indicator + batch_size
if end_indicator > self._num_examples:
if self._need_shuffle:
self._shuffle_data()
self._indicator = 0
end_indicator = batch_size
else:
raise Exception("have no more examples")
if end_indicator > self._num_examples:
raise Exception("batch size is larger than all examples")
batch_data = self._data[self._indicator: end_indicator]
batch_labels = self._labels[self._indicator: end_indicator]
self._indicator = end_indicator
return batch_data, batch_labels
train_filenames = [os.path.join(CIFAR_DIR, 'data_batch_%d' % i) for i in range(1, 6)]
test_filenames = [os.path.join(CIFAR_DIR, 'test_batch')]
train_data = CifarData(train_filenames, True)
test_data = CifarData(test_filenames, False)
def inception_block(x,
output_channel_for_each_path,
name):
"""inception block implementation"""
"""
Args:
- x:
- output_channel_for_each_path: eg: [10, 20, 5]
- name:
- 图片的宽和高没有改变,通道数改变了(卷积的通道加池化后的通道,池化不改变通道数目)
"""
with tf.variable_scope(name):
conv1_1 = tf.layers.conv2d(x,
output_channel_for_each_path[0],
(1, 1),
strides = (1,1),
padding = 'same',
activation = tf.nn.relu,
name = 'conv1_1')
conv3_3 = tf.layers.conv2d(x,
output_channel_for_each_path[1],
(3, 3),
strides = (1,1),
padding = 'same',
activation = tf.nn.relu,
name = 'conv3_3')
conv5_5 = tf.layers.conv2d(x,
output_channel_for_each_path[2],
(5, 5),
strides = (1,1),
padding = 'same',
activation = tf.nn.relu,
name = 'conv5_5')
max_pooling = tf.layers.max_pooling2d(x,
pool_size = (2, 2),
strides = (2, 2),
padding = 'valid',
name = 'max_pooling')
max_pooling_shape = max_pooling.get_shape().as_list()[1:]
input_shape = x.get_shape().as_list()[1:]
width_padding = (input_shape[0] - max_pooling_shape[0]) // 2
height_padding = (input_shape[1] - max_pooling_shape[1]) // 2
padded_pooling = tf.pad(max_pooling,
[[0, 0],
[width_padding, width_padding],
[height_padding, height_padding],
[0, 0]])
# concat : 指定轴拼接,其他轴的形状要相同
concat_layer = tf.concat([conv1_1, conv3_3, conv5_5, padded_pooling],
axis = 3)
# print(conv1_1.get_shape().as_list(),
# conv3_3.get_shape().as_list(),
# conv5_5.get_shape().as_list(),
# padded_pooling.get_shape().as_list(),
# concat_layer.get_shape().as_list())
return concat_layer
x = tf.placeholder(tf.float32, [None, 3072])
y = tf.placeholder(tf.int64, [None])
# [None], eg: [0,5,6,3]
x_image = tf.reshape(x, [-1, 3, 32, 32])
# 32*32
x_image = tf.transpose(x_image, perm=[0, 2, 3, 1])
# conv1: 神经元图, feature_map, 输出图像
conv1 = tf.layers.conv2d(x_image,
32, # output channel number
(3,3), # kernel size
strides = (1, 1),
padding = 'same',
activation = tf.nn.relu,
name = 'conv1')
pooling1 = tf.layers.max_pooling2d(conv1,
pool_size = (2, 2), # kernel size
strides = (2, 2), # stride
padding = 'same',
name = 'pool1')
inception_2a = inception_block(pooling1,
[16, 16, 16],
name = 'inception_2a')
inception_2b = inception_block(inception_2a,
[16, 16, 16],
name = 'inception_2b')
pooling2 = tf.layers.max_pooling2d(inception_2b,
pool_size = (2, 2), # kernel size
strides = (2, 2), # stride
padding='valid',
name = 'pool2')
inception_3a = inception_block(pooling2,
[16, 16, 16],
name = 'inception_3a')
inception_3b = inception_block(inception_3a,
[16, 16, 16],
name = 'inception_3b')
pooling3 = tf.layers.max_pooling2d(inception_3b,
(2, 2), # kernel size
(2, 2), # stride
name = 'pool3')
flatten = tf.layers.flatten(pooling3)
y_ = tf.layers.dense(flatten, 10)
loss = tf.losses.sparse_softmax_cross_entropy(labels=y, logits=y_)
# indices
predict = tf.argmax(y_, 1)
correct_prediction = tf.equal(predict, y)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float64))
with tf.name_scope('train_op'):
train_op = tf.train.AdamOptimizer(1e-3).minimize(loss)
init = tf.global_variables_initializer()
batch_size = 20
train_steps = 1000
test_steps = 100
with tf.Session() as sess:
sess.run(init)
for i in range(train_steps):
batch_data, batch_labels = train_data.next_batch(batch_size)
loss_val, acc_val, _ = sess.run(
[loss, accuracy, train_op],
feed_dict={
x: batch_data,
y: batch_labels})
if (i+1) % 100 == 0:
print ('[Train] Step: %d, loss: %4.5f, acc: %4.5f'% (i+1, loss_val, acc_val))
if (i+1) % 1000 == 0:
test_data = CifarData(test_filenames, False)
all_test_acc_val = []
for j in range(test_steps):
test_batch_data, test_batch_labels \
= test_data.next_batch(batch_size)
test_acc_val = sess.run(
[accuracy],
feed_dict = {
x: test_batch_data,
y: test_batch_labels
})
all_test_acc_val.append(test_acc_val)
test_acc = np.mean(all_test_acc_val)
print ('[Test ] Step: %d, acc: %4.5f' % (i+1, test_acc))