Google Net Inception V3的上手报告

Google Net Inception V3的上手报告

1.如何下载inception-2015-12-05.tgz文件?

下载地址为:http://download.tensorflow.org/models/image/imagenet/inception-2015-12-05.tgz

(需要注意的是,inception-2015-12-05.tgz在inception_model文件夹目录下,img文件夹为存放需要识别图片的文件夹,img与inception_model,inception_log,Unzip.py,Load.py在同一文件目录下!
在这里插入图片描述

在这里插入图片描述

2.如何解压inception-2015-12-05.tgz文件并保存网络结构?

新建Unzip.py文件,添加以下代码并运行:

import tensorflow as tf
import os
import tarfile

#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-2015-12-05.tgz"
filepath = os.path.join(inception_pretrain_model_dir, 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.FastGFile(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()

3.如何载入训练好的Inception V3网络模型?

新建Load.py文件,添加以下代码并运行:(需要注意的是,把需要识别的图片放在img文件夹目录下,格式为.jpg/.jepg)

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

class NodeLookup(object):
    def __init__(self):  
        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.FastGFile('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('img/'):
        for file in files:
            #载入图片
            image_data = tf.gfile.FastGFile(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
            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()

4.样例的测试情况?

图片为:

在这里插入图片描述

测试结果为:

img/car.jpg
crane (score = 0.75562)
moving van (score = 0.03443)
tow truck, tow car, wrecker (score = 0.02511)
snowplow, snowplough (score = 0.02426)
garbage truck, dustcart (score = 0.01032)

img/flower.jpg
hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa (score = 0.64947)
earthstar (score = 0.20885)
coral fungus (score = 0.01842)
gyromitra (score = 0.01142)
yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum (score = 0.00741)

img/fruit.jpg
orange (score = 0.63299)
lemon (score = 0.22070)
hip, rose hip, rosehip (score = 0.07571)
pot, flowerpot (score = 0.00627)
grocery store, grocery, food market, market (score = 0.00320)

说实话,这精度也就还行吧,毕竟是以前的版本了。

猜你喜欢

转载自blog.csdn.net/acceptedday/article/details/104126610