tensorflow入门实践（六）：调用预训练好的模型进行分类

环境：ubuntu16.04+tensorflow+cpu

文件路径：/home/qf/tensorflow/tf/tf6

用别人训练好的模型来进行图像分类

首先下载预训练的模型，放到model中，

model中如图所示

其中tensorflow_inception_graph.pb为预训练模型，tf-master/imagenet/文件夹下的

imagenet_2012_challenge_label_map_proto.pbtxt和 imagenet_synset_to_human_label_map.txt分别为电脑和人看的标签文件

# -*- coding: utf-8 -*-

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

model_dir='/home/qf/tensorflow/tf/tf6/model/'
image='/home/qf/tensorflow/tf/tf6/cat.jpg'


#transform label txt to txt which human can recongize 
##将类别ID转换为人类易读的标签
class NodeLookup(object):
  def __init__(self,
               label_lookup_path=None,
               uid_lookup_path=None):
    if not label_lookup_path:
      label_lookup_path = os.path.join(
          model_dir, 'tf-master/imagenet/imagenet_2012_challenge_label_map_proto.pbtxt')
    if not uid_lookup_path:
      uid_lookup_path = os.path.join(
          model_dir, 'tf-master/imagenet/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):
    if not tf.gfile.Exists(uid_lookup_path):
      tf.logging.fatal('File does not exist %s', uid_lookup_path)
    if not tf.gfile.Exists(label_lookup_path):
      tf.logging.fatal('File does not exist %s', label_lookup_path)

    # Loads mapping from string UID to human-readable string
    proto_as_ascii_lines = tf.gfile.GFile(uid_lookup_path).readlines()
    uid_to_human = {}
    p = re.compile(r'[n\d]*[ \S,]*')
    for line in proto_as_ascii_lines:
      parsed_items = p.findall(line)
      uid = parsed_items[0]
      human_string = parsed_items[2]
      uid_to_human[uid] = human_string

    # Loads mapping from string UID to integer node ID.
    node_id_to_uid = {}
    proto_as_ascii = tf.gfile.GFile(label_lookup_path).readlines()
    for line in proto_as_ascii:
      if line.startswith('  target_class:'):
        target_class = int(line.split(': ')[1])
      if line.startswith('  target_class_string:'):
        target_class_string = line.split(': ')[1]
        node_id_to_uid[target_class] = target_class_string[1:-2]

    # Loads the final mapping of integer node ID to human-readable string
    node_id_to_name = {}
    for key, val in node_id_to_uid.items():
      if val not in uid_to_human:
        tf.logging.fatal('Failed to locate: %s', val)
      name = uid_to_human[val]
      node_id_to_name[key] = name

    return node_id_to_name

  def id_to_string(self, node_id):
    if node_id not in self.node_lookup:
      return ''
    return self.node_lookup[node_id]

#read pre-trained  Inception-v3 model to construct graph
def create_graph():
##读取训练好的Inception-v3模型来创建graph
  with tf.gfile.FastGFile(os.path.join(
      model_dir, 'tensorflow_inception_graph.pb'), 'rb') as f:  #load model
    graph_def = tf.GraphDef()
    graph_def.ParseFromString(f.read())
    tf.import_graph_def(graph_def, name='')


#construct graph
create_graph()
'''
#read image 
#image_data = tf.gfile.FastGFile(image, 'rb').read()

sess=tf.Session()
# the Inception-v3 model's last layer --softmax
##Inception-v3模型的最后一层softmax的输出
softmax_tensor= sess.graph.get_tensor_by_name('softmax:0')
#input image and get softmax value（shape=(1,1008)）
predictions = sess.run(softmax_tensor,{'DecodeJpeg/contents:0': image_data})
#(1,1008)->(1008,)
predictions = np.squeeze(predictions)

# ID --> English string label.
node_lookup = NodeLookup()
#take out the top 5 highest probability values (top-5)
top_5 = predictions.argsort()[-5:][::-1]
for node_id in top_5:
  human_string = node_lookup.id_to_string(node_id)
  score = predictions[node_id]
  print('%s (score = %.5f)' % (human_string, score))
  
sess.close()
'''
##################################################
#上面为对单幅图测试，若对多幅图测试代码如下

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.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 = sess.run(softmax_tensor,{'DecodeGif/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()