tensorflow迁移学习。运用google训练好的Inception-v3模型.zip

# -*- coding: utf-8 -*- import glob import os.path import random import numpy as np import tensorflow as tf from tensorflow.python.platform import gfile #Inception-v3模型瓶颈层的节点个数 BOTTENECK_TENSOR_SIZE = 2048 BOTTENECK_TENSOR_NAME='pool_3/_reshape:0' #图像输入张量对应名称 JPEG_DATA_TENSOR_NAME='DecodeJpeg/contents:0' #下载的谷歌训练好的Inception-v3模型文件目录 MODEL_DIR='/Users/yifanyang/Downloads/inception_dec_2015' #下载的谷歌训练好的Inception-v3模型文件名 MODEL_FILE='tensorflow_inception_graph.pb' #将模型计算得到的特征向量保存在文件中，免去重复计算 CACHE_DIR='/Users/yifanyang/Documents/Inception_v3' #图片数据文件夹，每一个子文件夹代表一个需要区分的类别 INPUT_DATA='/Users/yifanyang/Downloads/flower_photos' #验证的数据百分比 VALIDATION_PERCENTAGE = 10 #测试的数据百分比 TEST_PERCENTAGE=10 #定义神经网络的设置 LEARNING_RATE = 0.01 STEPS= 4000 BATCH = 100 # 3. 把样本中所有的图片列表并按训练、验证、测试数据分开 def create_image_lists(testing_percentage, validation_percentage): result = {} #获取当前目录下的所有子目录 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 #获取当前目录下的有效图片文件夹 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() # 初始化当前训练集，测试数据集和验证数据集 training_images = [] testing_images = [] validation_images = [] for file_name in file_list: base_name = os.path.basename(file_name) # 随机划分数据到训练数据集，测试数据集和验证数据集 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 # 4. 定义函数通过类别名称、所属数据集和图片编号获取一张图片的地址 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 # 5. 定义函数获取Inception-v3模型处理之后的特征向量的文件地址 def get_bottleneck_path(image_lists, label_name, index, category): return get_image_path(image_lists, CACHE_DIR, label_name, index, category) + '.txt' # 6. 定义函数使用加载的训练好的Inception-v3模型处理一张图片，得到这个图片的特征向量 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 # 7. 定义函数会先试图寻找已经计算且保存下来的特征向量，如果找不到则先计算这个特征向量，然后保存到文件 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 # 8. 这个函数随机获取一个batch的图片作为训练数据 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 # 9. 这个函数获取全部的测试数据，并计算正确率 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 # 10. 定义主函数 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=[BOTTENECK_TENSOR_NAME, JPEG_DATA_TENSOR_NAME]) # 定义新的神经网络输入 bottleneck_input = tf.placeholder(tf.float32, [None, BOTTENECK_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([BOTTENECK_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) # 定义交叉熵损失函数。 cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits, 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�