Tensorflow 卷积神经网络 Inception

 Inception-v3模型结构：

Inception-v3简介：

1.基于大滤波器尺寸分解卷积

在视觉网络中，预期相近激活的输出是高度相关的。因此，我们可以预期，它们的激活可以在聚合之前被减少，并且这应该会导致类似的富有表现力的局部表示。

全卷积网络 减少计算可以提高效率

2.分解到更小的卷积

5×5换2个3×3

共享权重 减少参数数量

3.空间分解为不对称卷积

可以通过1×n卷积和后面接一个n×1卷积替换任何n×n卷积，并且随着n增长，计算成本节省显著增加

4 利用辅助分类器

辅助分类器起着正则化项的作用

5 有效的网格尺寸减少

池化

先池化再卷积 产生瓶颈

先卷积再池化 计算效率变差

图10。缩减网格尺寸的同时扩展滤波器组的Inception模块。它不仅廉价并且避免了原则1中提出的表示瓶颈。右侧的图表示相同的解决方案，但是从网格大小而不是运算的角度来看。

7. 通过标签平滑进行模型正则化

谷歌提供的训练好的Inception-v3模型：  https://storage.googleapis.com/download.tensorflow.org/models/inception_dec_2015.zip

案例使用的数据集： http://download.tensorflow.org/example_images/flower_photos.tgz

数据集文件解压后，包含5个子文件夹，子文件夹的名称为花的名称，代表了不同的类别。平均每一种花有734张图片，图片是RGB色彩模式，大小也不相同。

"""

Created on Tue Apr 24 10:11:28 2018

@author: admin

@author: tz_zs

卷积神经网络 Inception-v3模型 迁移学习

"""

import glob

import os.path

import random

import numpy as np

import tensorflow as tf

from tensorflow.python.platform import gfile

BOTTLENECK_TENSOR_SIZE = 2048

BOTTLENECK_TENSOR_NAME = 'pool_3/_reshape:0'

JPEG_DATA_TENSOR_NAME = 'DecodeJpeg/contents:0'

MODEL_DIR = 'E:/DeepLearning/Git/cnn/inception_dec_2015'

MODEL_FILE = 'tensorflow_inception_graph.pb'

CACHE_DIR = 'tmp/bottleneck'

INPUT_DATA = 'E:/DeepLearning/Git/cnn/flower_photos'

MODEL_SAVE_PATH="E:/DeepLearning/Git/cnn/model"

VALIDATION_PERCENTAGE = 10

TEST_PERCENTACE = 10

LEARNING_RATE = 0.01

STEPS = 200

BATCH = 100

def create_image_lists(testing_percentage, validation_percentage):

"""

这个函数把数据集分成训练，验证，测试三部分

:param testing_percentage:测试的数据百分比 10

:param validation_percentage:验证的数据百分比 10

:return:

"""

result = {}

sub_dirs = [x[0] for x in os.walk(INPUT_DATA)]

is_root_dir = True

for sub_dir in sub_dirs:

if is_root_dir:

is_root_dir = False

continue

extensions = ['jpg', 'jepg', '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

label_name = dir_name.lower()

training_images = []

testing_images = []

validation_images = []

for file_name in file_list:

base_name = os.path.basename(file_name)

chance = np.random.randint(100)

if chance < validation_percentage:

validation_images.append(base_name)

elif chance < (testing_percentage + validation_percentage):

testing_images.append(base_name)

else:

training_images.append(base_name)

result[label_name] = {

'dir': dir_name,

'training': training_images,

'testing': testing_images,

'validation': validation_images

}

return result

def get_image_path(image_lists, image_dir, label_name, index, category):

"""

:param image_lists:所有图片信息

:param image_dir:根目录 （ 图片特征向量根目录 CACHE_DIR | 图片原始路径根目录 INPUT_DATA ）

:param label_name:类别的名称（ daisy|dandelion|roses|sunflowers|tulips ）

:param index:编号

:param category:所属的数据集（ training|testing|validation ）

:return: 一张图片的地址

"""

label_lists = image_lists[label_name]

category_list = label_lists[category]

mod_index = index % len(category_list)

base_name = category_list[mod_index]

sub_dir = label_lists['dir']

full_path = os.path.join(image_dir, sub_dir, base_name)

return full_path

def get_bottleneck_path(image_lists, label_name, index, category):

return get_image_path(image_lists, CACHE_DIR, label_name, index, category) + '.txt'

def run_bottleneck_on_image(sess, image_data, image_data_tensor, bottleneck_tensor):

"""

:param sess:

:param image_data:图片内容

:param image_data_tensor:

:param bottleneck_tensor:

:return:

"""

bottleneck_values = sess.run(bottleneck_tensor, {image_data_tensor: image_data})

bottleneck_values = np.squeeze(bottleneck_values)

return bottleneck_values

def get_or_create_bottleneck(sess, image_lists, label_name, index, category, jpeg_data_tensor, bottleneck_tensor):

"""

:param sess:

:param image_lists:

:param label_name:类别名

:param index:图片编号

:param category:

:param jpeg_data_tensor:

:param bottleneck_tensor:

:return:

"""

label_lists = image_lists[label_name]

sub_dir = label_lists['dir']

sub_dir_path = os.path.join(CACHE_DIR, sub_dir)

if not os.path.exists(sub_dir_path): os.makedirs(sub_dir_path)

bottleneck_path = get_bottleneck_path(image_lists, label_name, index, category)

if not os.path.exists(bottleneck_path):

image_path = get_image_path(image_lists, INPUT_DATA, label_name, index, category)

image_data = gfile.FastGFile(image_path, 'rb').read()

bottleneck_values = run_bottleneck_on_image(sess, image_data, jpeg_data_tensor, bottleneck_tensor)

bottleneck_string = ','.join(str(x) for x in bottleneck_values)

with open(bottleneck_path, 'w') as bottleneck_file:

bottleneck_file.write(bottleneck_string)

else:

with open(bottleneck_path, 'r') as bottleneck_file:

bottleneck_string = bottleneck_file.read()

bottleneck_values = [float(x) for x in bottleneck_string.split(',')]

return bottleneck_values

def get_random_cached_bottlenecks(sess, n_classes, image_lists, how_many, category, jpeg_data_tensor,

bottleneck_tensor):

"""

:param sess:

:param n_classes: 类别数量

:param image_lists:

:param how_many: 一个batch的数量

:param category: 所属的数据集

:param jpeg_data_tensor:

:param bottleneck_tensor:

:return: 特征向量列表，类别列表

"""

bottlenecks = []

ground_truths = []

for _ in range(how_many):

label_index = random.randrange(n_classes)

label_name = list(image_lists.keys())[label_index]

image_index = random.randrange(65536)

bottleneck = get_or_create_bottleneck(sess, image_lists, label_name, image_index, category, jpeg_data_tensor,

bottleneck_tensor)

ground_truth = np.zeros(n_classes, dtype=np.float32)

ground_truth[label_index] = 1.0

bottlenecks.append(bottleneck)

ground_truths.append(ground_truth)

return bottlenecks, ground_truths

def get_test_bottlenecks(sess, image_lists, n_classes, jpeg_data_tensor, bottleneck_tensor):

bottlenecks = []

ground_truths = []

label_name_list = list(image_lists.keys())

for label_index, label_name in enumerate(label_name_list):

category = 'testing'

for index, unused_base_name in enumerate(image_lists[label_name][category]):

'''''

print(index, unused_base_name)

0 10386503264_e05387e1f7_m.jpg

1 1419608016_707b887337_n.jpg

2 14244410747_22691ece4a_n.jpg

...

105 9467543719_c4800becbb_m.jpg

106 9595857626_979c45e5bf_n.jpg

107 9922116524_ab4a2533fe_n.jpg

'''

bottleneck = get_or_create_bottleneck(

sess, image_lists, label_name, index, category, jpeg_data_tensor, bottleneck_tensor)

ground_truth = np.zeros(n_classes, dtype=np.float32)

ground_truth[label_index] = 1.0

bottlenecks.append(bottleneck)

ground_truths.append(ground_truth)

return bottlenecks, ground_truths

def main(_):

image_lists = create_image_lists(TEST_PERCENTACE, VALIDATION_PERCENTAGE)

n_classes = len(image_lists.keys())

with gfile.FastGFile(os.path.join(MODEL_DIR, MODEL_FILE), 'rb') as f:

graph_def = tf.GraphDef()

graph_def.ParseFromString(f.read())

bottleneck_tensor, jpeg_data_tensor = tf.import_graph_def(graph_def, return_elements=[BOTTLENECK_TENSOR_NAME,

JPEG_DATA_TENSOR_NAME])

bottleneck_input = tf.placeholder(tf.float32, [None, BOTTLENECK_TENSOR_SIZE], name='BottleneckInputPlaceholder')

ground_truth_input = tf.placeholder(tf.float32, [None, n_classes], name='GroundTruthInput')

with tf.name_scope('final_training_ops'):

weights = tf.Variable(tf.truncated_normal([BOTTLENECK_TENSOR_SIZE, n_classes], stddev=0.001))

biases = tf.Variable(tf.zeros([n_classes]))

logits = tf.matmul(bottleneck_input, weights) + biases

final_tensor = tf.nn.softmax(logits)

cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=ground_truth_input)

cross_entropy_mean = tf.reduce_mean(cross_entropy)

train_step = tf.train.GradientDescentOptimizer(LEARNING_RATE).minimize(cross_entropy_mean)

with tf.name_scope('evaluation'):

correct_prediction = tf.equal(tf.argmax(final_tensor, 1), tf.argmax(ground_truth_input, 1))

evaluation_step = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

with tf.Session(config=tf.ConfigProto(log_device_placement=True)) as sess:

init = tf.global_variables_initializer()

sess.run(init)

print( sess.run(init))

for i in range(STEPS):

train_bottlenecks, train_ground_truth = get_random_cached_bottlenecks(sess, n_classes, image_lists, BATCH,

'training', jpeg_data_tensor,

bottleneck_tensor)

sess.run(train_step,

feed_dict={bottleneck_input: train_bottlenecks, ground_truth_input: train_ground_truth})

if i % 100 == 0 or i + 1 == STEPS:

validation_bottlenecks, validation_ground_truth = get_random_cached_bottlenecks(sess, n_classes,

image_lists, BATCH,

'validation',

jpeg_data_tensor,

bottleneck_tensor)

validation_accuracy = sess.run(evaluation_step, feed_dict={bottleneck_input: validation_bottlenecks,

ground_truth_input: validation_ground_truth})

print('Step %d: Validation accuracy on random sampled %d examples = %.1f%%' % (

i, BATCH, validation_accuracy * 100))

test_bottlenecks, test_ground_truth = get_test_bottlenecks(sess, image_lists, n_classes, jpeg_data_tensor,

bottleneck_tensor)

test_accuracy = sess.run(evaluation_step,

feed_dict={bottleneck_input: test_bottlenecks, ground_truth_input: test_ground_truth})

print('Final test accuracy = %.1f%%' % (test_accuracy * 100))

if __name__ == '__main__':

tf.app.run()

相关知识

深度学习之基于Tensorflow卷积神经网络花卉识别系统
几个卷积神经网络（CNN）可视化的网站
基于卷积神经网络的花卉图像分类研究（32页）
基于卷积神经网络的皮肤病诊断系统研究
【花卉识别系统】Python+卷积神经网络算法+人工智能+深度学习+图像识别+算法模型
TensorFlow学习记录（八）
满满干货！一文快速实现CNN(卷积神经网络)识别花朵
基于深度卷积神经网络的移动端花卉识别系统
花卉识别(tensorflow)
基于卷积神经网络的花卉识别

网址: Tensorflow 卷积神经网络 Inception https://www.huajiangbk.com/newsview343170.html