深度学习大部分时间花费在利用海量的数据训练出一个精确的模型,并且对训练主机的性能有较高的要求。那么能不能直接使用别人训练好的模型,免去繁琐的训练过程以及超高配置的机器要求?答案是肯定的。
以识别下面这张图为例
先上结果:
teddy, teddy bear (score = 0.99959)
toyshop (score = 0.00018)
ballpoint, ballpoint pen, ballpen, Biro (score = 0.00003)
mortarboard (score = 0.00001)
hamper (score = 0.00001)
从结果可以看出来,识别此图像为泰迪熊的可能性为99.959%。精度非常高。
运行环境:
Tensroflow 1.2 Ubuntu 16.04.1 Python 2.7 Pycharm
完整python代码如下:
# -*- coding: utf-8 -*-
import tensorflow as tf
import numpy as np
import re
import os
model_dir='./imagenet/'
image='./imagenet/teddy.jpg'
#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, 'imagenet_2012_challenge_label_map_proto.pbtxt')
if not uid_lookup_path:
uid_lookup_path = os.path.join(
model_dir, '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]
#读取训练好的Inception-v3模型来创建graph
def create_graph():
with tf.gfile.FastGFile(os.path.join(
model_dir, 'classify_image_graph_def.pb'), 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
tf.import_graph_def(graph_def, name='')
#读取图片
image_data = tf.gfile.FastGFile(image, 'rb').read()
#创建graph
create_graph()
sess=tf.Session()
#Inception-v3模型的最后一层softmax的输出
softmax_tensor= sess.graph.get_tensor_by_name('softmax:0')
#输入图像数据,得到softmax概率值(一个shape=(1,1008)的向量)
predictions = sess.run(softmax_tensor,{'DecodeJpeg/contents:0': image_data})
#(1,1008)->(1008,)
predictions = np.squeeze(predictions)
# ID --> English string label.
node_lookup = NodeLookup()
#取出前5个概率最大的值(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()
练好的模型可以由此获得:点击打开链接
参考:
http://www.cnblogs.com/denny402/