TF - Inception-V3模型进行图片分类

• Inception-v3

ImageNet数据集包含1500万张图片，22000个类别。
Google在大型图像数据库ImageNet上训练好的一个 CNN模型：Inception-v3 ，这个模型可以直接用来进行图像分类。Inception v3模型大约有2500万个参数，分类一张图像就用了50亿的乘加指令。采用谷歌已经训练好的模型，在个人电脑上可以快速完成图片分类。

Inception模型介绍

• 下载Inception-v3 并 查看结构

import tensorflow as tf
import os
import tarfile
import requests

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

# inception模型下载地址
inception_pretrain_model_url = 'http://download.tensorflow.org/models/image/imagenet/inception-2015-12-05.tgz'

# 模型存放地址
inception_pretrain_model_dir = "inception_model"
if not os.path.exists(inception_pretrain_model_dir):
    os.makedirs(inception_pretrain_model_dir)

# 获取文件名，以及文件路径
filename = inception_pretrain_model_url.split('/')[-1]
filepath = os.path.join(inception_pretrain_model_dir, filename)

# 下载模型
if not os.path.exists(filepath):
    print("download: ", filename)
    r = requests.get(inception_pretrain_model_url, stream=True)
    with open(filepath, 'wb') as f:
        for chunk in r.iter_content(chunk_size=1024):
            if chunk:
                f.write(chunk)
print("finish: ", filename)
# 解压文件
tarfile.open(filepath, 'r:gz').extractall(inception_pretrain_model_dir)

# 模型结构存放文件
log_dir = 'inception_log'
if not os.path.exists(log_dir):
    os.makedirs(log_dir)

# classify_image_graph_def.pb为google训练好的模型
inception_graph_def_file = os.path.join(inception_pretrain_model_dir, 'classify_image_graph_def.pb')
with tf.Session() as sess:
    # 创建一个图来存放google训练好的模型
    with tf.gfile.GFile(inception_graph_def_file, 'rb') as f:
        graph_def = tf.GraphDef()
        graph_def.ParseFromString(f.read())
        tf.import_graph_def(graph_def, name='')
    # 保存图的结构
    writer = tf.summary.FileWriter(log_dir, sess.graph)
    writer.close()

下载解压，读取pb文件保存为结构图

查看图

• 使用Inception-v3做各种图像识别

import tensorflow as tf
import os
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'


class NodeLookup(object):
    def __init__(self):  # 类的初始化
        label_lookup_path = 'inception_model/imagenet_2012_challenge_label_map_proto.pbtxt'
        uid_lookup_path = 'inception_model/imagenet_synset_to_human_label_map.txt'
        self.node_lookup = self.load(label_lookup_path, uid_lookup_path)

    def load(self, label_lookup_path, uid_lookup_path):
        # 加载分类字符串n********对应分类名称的文件
        proto_as_ascii_lines = tf.gfile.GFile(uid_lookup_path).readlines()
        uid_to_human = {}
        # 一行一行读取数据
        for line in proto_as_ascii_lines:
            # 去掉换行符
            line = line.strip('\n')
            # 按照'\t'分割
            parsed_items = line.split('\t')
            # 获取分类编号
            uid = parsed_items[0]
            # 获取分类名称
            human_string = parsed_items[1]
            # 保存编号字符串n********与分类名称映射关系
            uid_to_human[uid] = human_string

        # 加载分类字符串n********对应分类编号1-1000的文件
        proto_as_ascii = tf.gfile.GFile(label_lookup_path).readlines()
        node_id_to_uid = {}
        for line in proto_as_ascii:
            if line.startswith('  target_class:'):
                # 获取分类编号1-1000
                target_class = int(line.split(': ')[1])
            if line.startswith('  target_class_string:'):
                # 获取编号字符串n********
                target_class_string = line.split(': ')[1]
                # 保存分类编号1-1000与编号字符串n********映射关系
                node_id_to_uid[target_class] = target_class_string[1:-2]

        # 建立分类编号1-1000对应分类名称的映射关系
        node_id_to_name = {}
        for key, val in node_id_to_uid.items():
            # 获取分类名称
            name = uid_to_human[val]
            # 建立分类编号1-1000到分类名称的映射关系
            node_id_to_name[key] = name
        return node_id_to_name

    # 传入分类编号1-1000返回分类名称
    def id_to_string(self, node_id):
        if node_id not in self.node_lookup:
            return ''
        return self.node_lookup[node_id]


# 创建一个图来存放google训练好的模型
with tf.gfile.GFile('inception_model/classify_image_graph_def.pb', 'rb') as f:
    graph_def = tf.GraphDef()
    graph_def.ParseFromString(f.read())
    tf.import_graph_def(graph_def, name='')

with tf.Session() as sess:
    softmax_tensor = sess.graph.get_tensor_by_name('softmax:0')
    # 遍历目录
    for root, dirs, files in os.walk('images/'):
        for file in files:
            # 载入图片
            image_data = tf.gfile.GFile(os.path.join(root, file), 'rb').read()
            predictions = sess.run(softmax_tensor, {'DecodeJpeg/contents:0': image_data})  # 图片格式是jpg格式
            predictions = np.squeeze(predictions)  # 把结果转为1维数据

            # 打印图片路径及名称
            image_path = os.path.join(root, file)
            print(image_path)
            # 显示图片
            img = Image.open(image_path)
            plt.imshow(img)
            plt.axis('off')
            plt.show()

            # 排序(取倒数5个值，然后再对着五个之值倒序)
            top_k = predictions.argsort()[-5:][::-1]
            node_lookup = NodeLookup()
            for node_id in top_k:
                # 获取分类名称
                human_string = node_lookup.id_to_string(node_id)
                # 获取该分类的置信度
                score = predictions[node_id]
                print('%s (score = %.5f)' % (human_string, score))
            print()  # 换行

在代码同目录，新建一个images目录，放入图片

识别图片

运行结果：

images/cat.jpg
Egyptian cat (score = 0.26841)
tabby, tabby cat (score = 0.26439)
tiger cat (score = 0.10841)
paper towel (score = 0.01935)
window screen (score = 0.01144)

images/dog.jpg
dingo, warrigal, warragal, Canis dingo (score = 0.66988)
Eskimo dog, husky (score = 0.07884)
Siberian husky (score = 0.04236)
kelpie (score = 0.03799)
German shepherd, German shepherd dog, German police dog, alsatian (score = 0.01194)

images/ma.jpg
sorrel (score = 0.50042)
barrel, cask (score = 0.01471)
worm fence, snake fence, snake-rail fence, Virginia fence (score = 0.01373)
hartebeest (score = 0.01329)
Saluki, gazelle hound (score = 0.00933)

images/sea.jpg
seashore, coast, seacoast, sea-coast (score = 0.85161)
sandbar, sand bar (score = 0.09447)
lakeside, lakeshore (score = 0.02036)
promontory, headland, head, foreland (score = 0.00546)
catamaran (score = 0.00275)