本文小编为大家详细介绍“python怎么使用tensorflow进行图像分类”,内容详细,步骤清晰,细节处理妥当,希望这篇“python怎么使用tensorflow进行图像分类”文章能帮助大家解决疑惑,下面跟着小编的思路慢慢深入,一起来学习新知识吧。
正文
谷歌在大型图像数据库ImageNet上训练好了一个Inception-v3模型,这个模型我们可以直接用来进来图像分类。
下载完解压后,得到几个文件:
其中
classify_image_graph_def.pb 文件就是训练好的Inception-v3模型。
imagenet_synset_to_human_label_map.txt是类别文件。
随机找一张图片
对这张图片进行识别,看它属于什么类?
代码如下:先创建一个类NodeLookup来将softmax概率值映射到标签上。
然后创建一个函数create_graph()来读取模型。
读取图片进行分类识别
# -*- coding: utf-8 -*-import tensorflow as tfimport numpy as npimport reimport osmodel_dir='D:/tf/model/'image='d:/cat.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graphdef 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graphcreate_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()
最后输出
tiger cat (score = 0.40316)
Egyptian cat (score = 0.21686)
tabby, tabby cat (score = 0.21348)
lynx, catamount (score = 0.01403)
Persian cat (score = 0.00394)
读到这里,这篇“python怎么使用tensorflow进行图像分类”文章已经介绍完毕,想要掌握这篇文章的知识点还需要大家自己动手实践使用过才能领会,如果想了解更多相关内容的文章,欢迎关注编程网行业资讯频道。