Tensorflow inception-v3 图像识别
Table of Contents
1 使用 Inception-v3 做圖像識別
Inception-v3 是 1000 分類識別模型, 標籤有 1000 個分類.
import os import re import matplotlib.pyplot as plt import numpy as np import tensorflow as tf from PIL import Image 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): # 加載分類字符串 n******** 對應分類名稱的文件 proto_as_ascii_lines = tf.gfile.GFile(uid_lookup_path).readlines() uid_to_human = {} # 一行一行讀取數據 for line in proto_as_ascii_lines: # 去掉換行符 line = line.strip('\n') # 按照 '\t' 分割 parsed_items = line.split('\t') # 獲取分類編號 uid = parsed_items[0] # 獲取分類名稱 human_string = parsed_items[1] # 保存編號字符串 n********** 與分類名稱映射關係 # {"n01443243" : "gudgeon, Gobio gobio", ...} uid_to_human[uid] = human_string # 加載分類字符串 n******** 對應分類編號 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:'): # 獲取分類編號 1-1000 target_class = int(line.split(': ')[1]) if line.startswith(' target_class_string:'): # 獲取編號字符串 n******* target_class_string = line.split(': ')[1] # 保存分類編號1-1000 與編號字符串 n******** 映射關係 # {450:"n01443537", ...} node_id_to_uid[target_class] = target_class_string[1:-2] # 建立分類編號 1-1000 對應分類名稱的映射關係 node_id_to_name = {} for key, val in node_id_to_uid.items(): # 獲取分類名稱 name = uid_to_human[val] # 建立分類編號 1-1000 到分類名稱的映射關係 # node_id name # ---- -------------------- # {449: "tench, Tinca tinca", ....} node_id_to_name[key] = name return node_id_to_name # 傳入分類編號 1-1000 返回分類名稱 def id_to_string(self, node_id): if node_id not in self.node_lookup: return '' return self.node_lookup[node_id] # 創建一個空圖來加載 google 訓練好的模型 with tf.gfile.GFile('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: # 通過node名字加載你需要計算的 node softmax_tensor = sess.graph.get_tensor_by_name('softmax:0') # 遍歷目錄 for root, dirs, files in os.walk('images/'): for file in files: # 載入圖片 image_data = tf.gfile.FastGFile(os.path.join(root, file), 'rb').read() # 餵食數據給graph的入口placeholder predictions = sess.run(softmax_tensor, {'DecodeJpeg/contents:0': image_data}) # predictions 是一個1000維向量, 每一個位都是一個概率值. # (1000, 1) ==> (1000,) predictions = np.squeeze(predictions) # 結果轉換爲 1 維數據 # 打印圖片路徑及名稱 image_path = os.path.join(root, file) print(image_path) # 顯示圖片 img = Image.open(image_path) plt.imshow(img) plt.axis('off') plt.show() # 排序 # argsort 排序得到的是從小到大的list # # 對這5個值取倒序,將其變成從大到小 <-+ # | # 取最大的5個(其順序依然從小到大) | # | | # ---- ---- top_k = predictions.argsort()[-5:][::-1] node_lookup = NodeLookup() for node_id in top_k: # 獲取分類名稱 human_string = node_lookup.id_to_string(node_id) # 獲取該分類置信度 score = predictions[node_id] print('%s (score = %.5f)' % (human_string, score)) print()
/home/yiddi/git_repos/on_ml_tensorflow/inception_model/ imagenet_2012_challenge_label_map_proto.pbtxt # -*- protobuffer -*- # LabelMap from ImageNet 2012 full data set UID to int32 target class. entry { target_class: 449 target_class_string: "n01440764" -------------------------+ } | entry { | target_class: 450 | target_class_string: "n01443537" | } | entry { | target_class: 442 | target_class_string: "n01484850" | } | | ======================================================== | | /home/yiddi/git_repos/on_ml_tensorflow/inception_model/ | imagenet_synset_to_human_label_map.txt | | +--------------------------------------------------------+ v n01440764 tench, Tinca tinca ..... n01443537 goldfish, Carassius auratus ..... n01484850 great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias