图像识别与卷积神经网络
卷积层和池化层样例
import tensorflow as tf
import numpy as np
M = np.array([
[[1],[-1],[0]],
[[-1],[2],[1]],
[[0],[2],[-2]]
])
print "Matrix shape is: ",M.shape
"""
Matrix shape is: (3, 3, 1)
"""
filter_weight = tf.get_variable('weights', [2, 2, 1, 1], initializer = tf.constant_initializer([
[1, -1],
[0, 2]]))
biases = tf.get_variable('biases', [1], initializer = tf.constant_initializer(1))
M = np.asarray(M, dtype='float32')
M = M.reshape(1, 3, 3, 1)
x = tf.placeholder('float32', [1, None, None, 1])
conv = tf.nn.conv2d(x, filter_weight, strides = [1, 2, 2, 1], padding = 'SAME')
bias = tf.nn.bias_add(conv, biases)
pool = tf.nn.avg_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
with tf.Session() as sess:
tf.global_variables_initializer().run()
convoluted_M = sess.run(bias,feed_dict={x:M})
pooled_M = sess.run(pool,feed_dict={x:M})
print "convoluted_M: \n", convoluted_M
print "pooled_M: \n", pooled_M
"""
convoluted_M:
[[[[ 7.]
[ 1.]]
[[-1.]
[-1.]]]]
pooled_M:
[[[[ 0.25]
[ 0.5 ]]
[[ 1. ]
[-2. ]]]]
"""LeNet-5 模型
LeNet-5_inference.py
import tensorflow as tf
INPUT_NODE = 784
OUTPUT_NODE = 10
IMAGE_SIZE = 28
NUM_CHANNELS = 1
NUM_LABELS = 10
CONV1_DEEP = 32
CONV1_SIZE = 5
CONV2_DEEP = 64
CONV2_SIZE = 5
FC_SIZE = 512
def inference(input_tensor, train, regularizer):
with tf.variable_scope('layer1-conv1'):
conv1_weights = tf.get_variable(
"weight", [CONV1_SIZE, CONV1_SIZE, NUM_CHANNELS, CONV1_DEEP],
initializer=tf.truncated_normal_initializer(stddev=0.1))
conv1_biases = tf.get_variable("bias", [CONV1_DEEP], initializer=tf.constant_initializer(0.0))
conv1 = tf.nn.conv2d(input_tensor, conv1_weights, strides=[1, 1, 1, 1], padding='SAME')
relu1 = tf.nn.relu(tf.nn.bias_add(conv1, conv1_biases))
with tf.name_scope("layer2-pool1"):
pool1 = tf.nn.max_pool(relu1, ksize = [1,2,2,1],strides=[1,2,2,1],padding="SAME")
with tf.variable_scope("layer3-conv2"):
conv2_weights = tf.get_variable(
"weight", [CONV2_SIZE, CONV2_SIZE, CONV1_DEEP, CONV2_DEEP],
initializer=tf.truncated_normal_initializer(stddev=0.1))
conv2_biases = tf.get_variable("bias", [CONV2_DEEP], initializer=tf.constant_initializer(0.0))
conv2 = tf.nn.conv2d(pool1, conv2_weights, strides=[1, 1, 1, 1], padding='SAME')
relu2 = tf.nn.relu(tf.nn.bias_add(conv2, conv2_biases))
with tf.name_scope("layer4-pool2"):
pool2 = tf.nn.max_pool(relu2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
pool_shape = pool2.get_shape().as_list()
nodes = pool_shape[1] * pool_shape[2] * pool_shape[3]
reshaped = tf.reshape(pool2, [pool_shape[0], nodes])
with tf.variable_scope('layer5-fc1'):
fc1_weights = tf.get_variable("weight", [nodes, FC_SIZE],
initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None: tf.add_to_collection('losses', regularizer(fc1_weights))
fc1_biases = tf.get_variable("bias", [FC_SIZE], initializer=tf.constant_initializer(0.1))
fc1 = tf.nn.relu(tf.matmul(reshaped, fc1_weights) + fc1_biases)
if train: fc1 = tf.nn.dropout(fc1, 0.5)
with tf.variable_scope('layer6-fc2'):
fc2_weights = tf.get_variable("weight", [FC_SIZE, NUM_LABELS],
initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None: tf.add_to_collection('losses', regularizer(fc2_weights))
fc2_biases = tf.get_variable("bias", [NUM_LABELS], initializer=tf.constant_initializer(0.1))
logit = tf.matmul(fc1, fc2_weights) + fc2_biases
return logitLeNet5_train.py
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import LeNet5_infernece
import os
import numpy as np
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.01
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 6000
MOVING_AVERAGE_DECAY = 0.99
def train(mnist):
# 定义输出为4维矩阵的placeholder
x = tf.placeholder(tf.float32, [
BATCH_SIZE,
LeNet5_infernece.IMAGE_SIZE,
LeNet5_infernece.IMAGE_SIZE,
LeNet5_infernece.NUM_CHANNELS],
name='x-input')
y_ = tf.placeholder(tf.float32, [None, LeNet5_infernece.OUTPUT_NODE], name='y-input')
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
y = LeNet5_infernece.inference(x,False,regularizer)
global_step = tf.Variable(0, trainable=False)
# 定义损失函数、学习率、滑动平均操作以及训练过程。
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
cross_entropy_mean = tf.reduce_mean(cross_entropy)
loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY,
staircase=True)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
with tf.control_dependencies([train_step, variables_averages_op]):
train_op = tf.no_op(name='train')
# 初始化TensorFlow持久化类。
saver = tf.train.Saver()
with tf.Session() as sess:
tf.global_variables_initializer().run()
for i in range(TRAINING_STEPS):
xs, ys = mnist.train.next_batch(BATCH_SIZE)
reshaped_xs = np.reshape(xs, (
BATCH_SIZE,
LeNet5_infernece.IMAGE_SIZE,
LeNet5_infernece.IMAGE_SIZE,
LeNet5_infernece.NUM_CHANNELS))
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: reshaped_xs, y_: ys})
if i % 1000 == 0:
print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
def main(argv=None):
mnist = input_data.read_data_sets("../../../datasets/MNIST_data", one_hot=True)
train(mnist)
if __name__ == '__main__':
main()
"""
Extracting ../../../datasets/MNIST_data/train-images-idx3-ubyte.gz
Extracting ../../../datasets/MNIST_data/train-labels-idx1-ubyte.gz
Extracting ../../../datasets/MNIST_data/t10k-images-idx3-ubyte.gz
Extracting ../../../datasets/MNIST_data/t10k-labels-idx1-ubyte.gz
After 1 training step(s), loss on training batch is 5.95725.
After 1001 training step(s), loss on training batch is 0.664706.
After 2001 training step(s), loss on training batch is 0.670048.
After 3001 training step(s), loss on training batch is 0.638539.
After 4001 training step(s), loss on training batch is 0.743027.
After 5001 training step(s), loss on training batch is 0.638279.
"""Inception-v3 模型
在 LeNet-5 模型中，不同卷积层通过串联的方式连接在一起，而 Inception-v3 模型中的 Inception 结构是将不同的卷积层通过并联的方式结合在一起。从上图中，Inception 模块会首先使用不同尺寸的过滤器处理输入矩阵。虽然过滤器的大小不同，但如果所有的过滤器都使用全 0 填充且步长为 1，那么前向传播得到的结果矩阵的长和宽都与输入矩阵一致。这样经过不同过滤器处理的结果矩阵可以拼接成一个更深的矩阵。
卷积神经网络迁移学习
所谓迁移学习，就是将一个问题上训练好的模型通过简单的调整使其适用于一个新的问题。根据现有论文的结论，可以保留训练好的 Inception-v3 模型中的所有卷积层的参数，只是替换最后一层全连接层。在最后这一层全连接层之前的网路层称之为瓶颈层（bottleneck）。
data_process.py
import glob
import os.path
import numpy as np
import tensorflow as tf
from tensorflow.python.platform import gfile
# 原始输入数据的目录，这个目录下有5个子目录，每个子目录底下保存这属于该
# 类别的所有图片。
INPUT_DATA = '../../datasets/flower_photos'
# 输出文件地址。我们将整理后的图片数据通过numpy的格式保存。
OUTPUT_FILE = '../../datasets/flower_processed_data.npy'
# 测试数据和验证数据比例。
VALIDATION_PERCENTAGE = 10
TEST_PERCENTAGE = 10
# 读取数据并将数据分割成训练数据、验证数据和测试数据。
def create_image_lists(sess, testing_percentage, validation_percentage):
sub_dirs = [x[0] for x in os.walk(INPUT_DATA)]
is_root_dir = True
# 初始化各个数据集。
training_images = []
training_labels = []
testing_images = []
testing_labels = []
validation_images = []
validation_labels = []
current_label = 0
# 读取所有的子目录。
for sub_dir in sub_dirs:
if is_root_dir:
is_root_dir = False
continue
# 获取一个子目录中所有的图片文件。
extensions = ['jpg', 'jpeg', 'JPG', 'JPEG']
file_list = []
dir_name = os.path.basename(sub_dir)
for extension in extensions:
file_glob = os.path.join(INPUT_DATA, dir_name, '*.' + extension)
file_list.extend(glob.glob(file_glob))
if not file_list: continue
print "processing:", dir_name
i = 0
# 处理图片数据。
for file_name in file_list:
i += 1
# 读取并解析图片，将图片转化为299*299以方便inception-v3模型来处理。
image_raw_data = gfile.FastGFile(file_name, 'rb').read()
image = tf.image.decode_jpeg(image_raw_data)
if image.dtype != tf.float32:
image = tf.image.convert_image_dtype(image, dtype=tf.float32)
image = tf.image.resize_images(image, [299, 299])
image_value = sess.run(image)
# 随机划分数据聚。
chance = np.random.randint(100)
if chance < validation_percentage:
validation_images.append(image_value)
validation_labels.append(current_label)
elif chance < (testing_percentage + validation_percentage):
testing_images.append(image_value)
testing_labels.append(current_label)
else:
training_images.append(image_value)
training_labels.append(current_label)
if i % 200 == 0:
print i, "images processed."
current_label += 1
# 将训练数据随机打乱以获得更好的训练效果。
state = np.random.get_state()
np.random.shuffle(training_images)
np.random.set_state(state)
np.random.shuffle(training_labels)
return np.asarray([training_images, training_labels,
validation_images, validation_labels,
testing_images, testing_labels])
with tf.Session() as sess:
processed_data = create_image_lists(sess, TEST_PERCENTAGE, VALIDATION_PERCENTAGE)
# 通过numpy格式保存处理后的数据。
np.save(OUTPUT_FILE, processed_data)
"""
processing: roses
200 images processed.
400 images processed.
600 images processed.
processing: sunflowers
200 images processed.
400 images processed.
600 images processed.
processing: daisy
200 images processed.
400 images processed.
600 images processed.
processing: dandelion
200 images processed.
400 images processed.
600 images processed.
800 images processed.
processing: tulips
200 images processed.
400 images processed.
600 images processed.
"""fine_tuning.py
import glob
import os.path
import numpy as np
import tensorflow as tf
from tensorflow.python.platform import gfile
import tensorflow.contrib.slim as slim
# 加载通过TensorFlow-Slim定义好的inception_v3模型。
import tensorflow.contrib.slim.python.slim.nets.inception_v3 as inception_v3
# 处理好之后的数据文件。
INPUT_DATA = '../../datasets/flower_processed_data.npy'
# 保存训练好的模型的路径。
TRAIN_FILE = 'train_dir/model'
# 谷歌提供的训练好的模型文件地址。因为GitHub无法保存大于100M的文件，所以
# 在运行时需要先自行从Google下载inception_v3.ckpt文件。
CKPT_FILE = '../../datasets/inception_v3.ckpt'
# 定义训练中使用的参数。
LEARNING_RATE = 0.0001
STEPS = 300
BATCH = 32
N_CLASSES = 5
# 不需要从谷歌训练好的模型中加载的参数。
CHECKPOINT_EXCLUDE_SCOPES = 'InceptionV3/Logits,InceptionV3/AuxLogits'
# 需要训练的网络层参数明层，在fine-tuning的过程中就是最后的全联接层。
TRAINABLE_SCOPES='InceptionV3/Logits,InceptionV3/AuxLogit'
def get_tuned_variables():
exclusions = [scope.strip() for scope in CHECKPOINT_EXCLUDE_SCOPES.split(',')]
variables_to_restore = []
# 枚举inception-v3模型中所有的参数，然后判断是否需要从加载列表中移除。
for var in slim.get_model_variables():
excluded = False
for exclusion in exclusions:
if var.op.name.startswith(exclusion):
excluded = True
break
if not excluded:
variables_to_restore.append(var)
return variables_to_restore
def get_trainable_variables():
scopes = [scope.strip() for scope in TRAINABLE_SCOPES.split(',')]
variables_to_train = []
# 枚举所有需要训练的参数前缀，并通过这些前缀找到所有需要训练的参数。
for scope in scopes:
variables = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope)
variables_to_train.extend(variables)
return variables_to_train
def main():
# 加载预处理好的数据。
processed_data = np.load(INPUT_DATA)
training_images = processed_data[0]
n_training_example = len(training_images)
training_labels = processed_data[1]
validation_images = processed_data[2]
validation_labels = processed_data[3]
testing_images = processed_data[4]
testing_labels = processed_data[5]
print("%d training examples, %d validation examples and %d testing examples." % (
n_training_example, len(validation_labels), len(testing_labels)))
# 定义inception-v3的输入，images为输入图片，labels为每一张图片对应的标签。
images = tf.placeholder(tf.float32, [None, 299, 299, 3], name='input_images')
labels = tf.placeholder(tf.int64, [None], name='labels')
# 定义inception-v3模型。因为谷歌给出的只有模型参数取值，所以这里
# 需要在这个代码中定义inception-v3的模型结构。虽然理论上需要区分训练和
# 测试中使用到的模型，也就是说在测试时应该使用is_training=False，但是
# 因为预先训练好的inception-v3模型中使用的batch normalization参数与
# 新的数据会有出入，所以这里直接使用同一个模型来做测试。
with slim.arg_scope(inception_v3.inception_v3_arg_scope()):
logits, _ = inception_v3.inception_v3(
images, num_classes=N_CLASSES, is_training=True)
trainable_variables = get_trainable_variables()
# 定义损失函数和训练过程。
tf.losses.softmax_cross_entropy(
tf.one_hot(labels, N_CLASSES), logits, weights=1.0)
total_loss = tf.losses.get_total_loss()
train_step = tf.train.RMSPropOptimizer(LEARNING_RATE).minimize(total_loss)
# 计算正确率。
with tf.name_scope('evaluation'):
correct_prediction = tf.equal(tf.argmax(logits, 1), labels)
evaluation_step = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# 定义加载Google训练好的Inception-v3模型的Saver。
load_fn = slim.assign_from_checkpoint_fn(
CKPT_FILE,
get_tuned_variables(),
ignore_missing_vars=True)
# 定义保存新模型的Saver。
saver = tf.train.Saver()
with tf.Session() as sess:
# 初始化没有加载进来的变量。
init = tf.global_variables_initializer()
sess.run(init)
# 加载谷歌已经训练好的模型。
print('Loading tuned variables from %s' % CKPT_FILE)
load_fn(sess)
start = 0
end = BATCH
for i in range(STEPS):
_, loss = sess.run([train_step, total_loss], feed_dict={
images: training_images[start:end],
labels: training_labels[start:end]})
if i % 30 == 0 or i + 1 == STEPS:
saver.save(sess, TRAIN_FILE, global_step=i)
validation_accuracy = sess.run(evaluation_step, feed_dict={
images: validation_images, labels: validation_labels})
print('Step %d: Training loss is %.1f Validation accuracy = %.1f%%' % (
i, loss, validation_accuracy * 100.0))
start = end
if start == n_training_example:
start = 0
end = start + BATCH
if end > n_training_example:
end = n_training_example
# 在最后的测试数据上测试正确率。
test_accuracy = sess.run(evaluation_step, feed_dict={
images: testing_images, labels: testing_labels})
print('Final test accuracy = %.1f%%' % (test_accuracy * 100))
if __name__ == '__main__':
main()
"""
2965 training examples, 338 validation examples and 367 testing examples.
Loading tuned variables from ../../datasets/inception_v3.ckpt
INFO:tensorflow:Restoring parameters from ../../datasets/inception_v3.ckpt
Step 0: Training loss is 2.8 Validation accuracy = 18.6%
Step 30: Training loss is 2.2 Validation accuracy = 28.1%
Step 60: Training loss is 1.3 Validation accuracy = 61.2%
Step 90: Training loss is 0.6 Validation accuracy = 83.1%
Step 120: Training loss is 0.4 Validation accuracy = 87.9%
Step 150: Training loss is 0.4 Validation accuracy = 89.9%
Step 180: Training loss is 0.3 Validation accuracy = 91.1%
Step 210: Training loss is 0.3 Validation accuracy = 91.1%
Step 240: Training loss is 0.3 Validation accuracy = 90.8%
Step 270: Training loss is 0.3 Validation accuracy = 89.6%
Step 299: Training loss is 0.2 Validation accuracy = 91.7%
Final test accuracy = 92.6%
"""