简单迁移学习inception-v3各种图像的识别

   接着上一篇文章，上一篇文章中，我们下载了inception-v3的模型，接下来，我们进行简单的迁移学习，将物体进行分类。

下面是代码：

# coding: UTF-8import tensorflow as tfimport osimport numpy as npimport refrom PIL import Imageimport matplotlib.pyplot as pltclass 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 = {}        for line in proto_as_ascii_lines:            line = line.strip('\n')            parsed_items = line.split('\t')            uid = parsed_items[0]  # n15092227            human_string = parsed_items[1]            uid_to_human[uid] = human_string        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:'):                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]        node_id_to_name = {}        for key, val in node_id_to_uid.items():            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]# 创建一个图来存放google调整好的模型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('images/'):        for file in files:            image_data = tf.gfile.FastGFile(os.path.join(root, file), 'rb').read()            predictions = sess.run(softmax_tensor, {'DecodeJpeg/contents:0': image_data})            predictions = np.squeeze(predictions)            image_path = os.path.join(root, file)            print image_path            img = Image.open(image_path)            plt.imshow(img)            plt.axis('off')            plt.show()            top_k = predictions.argsort()[-5:][::-1]            node_lookup = NodeLookup()            for node_id in top_k:                human_string = node_lookup.id_to_string(node_id)                score = predictions[node_id]                print('%s (score=%.5f)' % (human_string, score))            print()

其中代码NodeLookup是类，作用是将inception-v3中1000个分类得分转换成类别的字符串，其中的文件如下所示：

imagenet_2012_challenge_label_map_proto.pbtxt

imagenet_synset_to_human_label_map.txt

从上面的图中可以很简单的看出来。

然后创建一个图用来存放调整好的google存放的权重的图。

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='')

然后创建会话，在会话中引进softmax的分类器，用softmax分类器进行预测predictions，其中，得到的predictions是二维的，

predictions = sess.run(softmax_tensor, {'DecodeJpeg/contents:0': image_data})

，将图片jped的格式传入。然后np.squeeze得到一维。

最后得到预测值。