基于tensorlfow的 inceptionv3 迁移学习图片分类

本文完整代码放在了github中了

准备数据集：

本文使用flowers数据集，地址：http://download.tensorflow.org/example_images/flower_photos.tgz ，下载后解压即可。
flower_photos文件夹下有5类花名，分别是daisy、dandelion、roses、sunflowers、tulips。

准备Inception-v3模型

模型地址：https://storage.googleapis.com/download.tensorflow.org/models/inception_dec_2015.zip ，下载后解压即可。

训练和验证：

新建tmp文件存放图片特征信息，执行python inception_v3.py，代码如下：

# coding=utf8

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 = './inception_dec_2015'
MODEL_FILE= 'tensorflow_inception_graph.pb'

CACHE_DIR = './tmp'
INPUT_DATA = './flower_photos'

VALIDATION_PERCENTAGE = 10
TEST_PERCENTAGE = 10

LEARNING_RATE = 0.01
STEPS = 20000
BATCH = 100


def create_image_lists(testing_percentage, validation_percentage):
    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', '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

        label_name = dir_name.lower()

        # 初始化
        training_images = []
        testing_images = []
        validation_images = []
        for file_name in file_list:
            base_name = os.path.basename(file_name)

            # 随机划分数据
            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,
        }
        print(label_name)
    return result


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

    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):
    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):
    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]):
            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_PERCENTAGE, VALIDATION_PERCENTAGE)
    n_classes = len(image_lists.keys())

    # 读取已经训练好的Inception-v3模型。
    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])

    # 定义新的神经网络输入
    bottleneck_input = tf.placeholder(tf.float32, [None, BOTTLENECK_TENSOR_SIZE], name='BottleneckInputPlaceholder')
    ground_truth_input = tf.placeholder(tf.float32, [None, n_classes], name='GroundTruthInput')

    # 定义一层全链接层
    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,name='logits_eval')

    # 定义交叉熵损失函数。
    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)

    # 计算正确率
    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))
    saver=tf.train.Saver()
    with tf.Session() as sess:

        sess.run(tf.global_variables_initializer())
        # 训练过程。
        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))
            if validation_accuracy >0.99:
                saver.save(sess,'./model/model_0.99.ckpt')
        # 在最后的测试数据上测试正确率。
        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))
        saver.save(sess,'./model/model.ckpt')
        sess.close()
if __name__ == '__main__':
    main()
    

测试单张图片

执行python test.py，完整代码如下：

import tensorflow as tf
import numpy as np

# 模型目录
CHECKPOINT_DIR = './model'
INCEPTION_MODEL_FILE = './inception_dec_2015/tensorflow_inception_graph.pb'

# inception-v3模型参数
BOTTLENECK_TENSOR_NAME = 'pool_3/_reshape:0'  # inception-v3模型中代表瓶颈层结果的张量名称
JPEG_DATA_TENSOR_NAME = 'DecodeJpeg/contents:0'  # 图像输入张量对应的名称
flower_dict = {0:'sunflowers',1:'dandelion',2:'dasiy',3:'roses',4:'tulips'}
# 测试数据
#file_path = './flower_photos/tulips/11746080_963537acdc.jpg'
#file_path = "./flower_photos/daisy/5547758_eea9edfd54_n.jpg"
#file_path = "./flower_photos/dandelion/7355522_b66e5d3078_m.jpg"
#file_path = "./flower_photos/roses/394990940_7af082cf8d_n.jpg"
#file_path = "./flower_photos/sunflowers/6953297_8576bf4ea3.jpg"
file_path = "./flower_photos/tulips/10791227_7168491604.jpg"



# 读取数据
image_data = tf.gfile.FastGFile(file_path, 'rb').read()

# 评估
checkpoint_file = tf.train.latest_checkpoint(CHECKPOINT_DIR)
with tf.Graph().as_default() as graph:
    with tf.Session().as_default() as sess:
        # 读取训练好的inception-v3模型
        with tf.gfile.FastGFile(INCEPTION_MODEL_FILE, 'rb') as f:
            graph_def = tf.GraphDef()
            graph_def.ParseFromString(f.read())

        # 加载inception-v3模型，并返回数据输入张量和瓶颈层输出张量
        bottleneck_tensor, jpeg_data_tensor = tf.import_graph_def(
            graph_def,
            return_elements=[BOTTLENECK_TENSOR_NAME, JPEG_DATA_TENSOR_NAME])

        # 使用inception-v3处理图片获取特征向量
        bottleneck_values = sess.run(bottleneck_tensor,
                                     {jpeg_data_tensor: image_data})
        # 将四维数组压缩成一维数组，由于全连接层输入时有batch的维度，所以用列表作为输入
        bottleneck_values = [np.squeeze(bottleneck_values)]
        print(checkpoint_file)
        # 加载元图和变量
        saver = tf.train.import_meta_graph('{}.meta'.format(checkpoint_file))
        saver.restore(sess, checkpoint_file)

        # 通过名字从图中获取输入占位符
        input_x = graph.get_operation_by_name(
            'BottleneckInputPlaceholder').outputs[0]

        # 我们想要评估的tensors
        predictions = graph.get_operation_by_name('evaluation/ArgMax').outputs[0]

        # 收集预测值
        all_predictions = []
        all_predictions = sess.run(predictions, {input_x: bottleneck_values})
print(flower_dict[all_predictions[0]])