Inception-v3是最新的一個模型，在ImageNet-2012上訓練進行分類。

與其他網路對比

AlexNet achieved by setting a top-5 error rate of 15.3% on the 2012 validation data set; BN-Inception-v2 achieved 6.66%; Inception-v3 reaches 3.46%.

How well do humans do on ImageNet Challenge? There’s a blog post by Andrej Karpathy who attempted to measure his own performance. He reached 5.1%

top-5 error rate.

我猜人類的識別率應該很大程度受限於一個人的知識水平。比如對於貓而言，我們只知道很少幾個品種，而計算機卻可以儲存很多品種的貓的資訊。

呼叫Python API

在cmd中輸入

cd tensorflow/models/image/imagenet
python classify_image.py

自動在官網下載訓練好的Inception-v3模型，和相關檔案(一張測試影象cropped_panda.jpg)

Inception-v3自動分類此影象，結果為

giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca (score = 0.88493)
indri, indris, Indri indri, Indri brevicaudatus (score = 0.00878)
lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens (score = 0.00317)
custard apple (score = 0.00149)
earthstar (score = 0.00127)

測試自定義影象，使用–image_file引數

python classify_iamge.py –image_file=img_dir

比如
1.

convertible (score = 0.52526)敞篷車
sports car, sport car (score = 0.34500)跑車
grille, radiator grille (score = 0.01084)
car wheel (score = 0.00232)
amphibian, amphibious vehicle (score = 0.00137)
前兩者置信度都挺高，30%+，那更合理的結果是不是敞篷跑車？
2.

Egyptian cat (score = 0.14357)埃及貓
tabby, tabby cat (score = 0.07122)
tiger cat (score = 0.06887)
Persian cat (score = 0.02849)
window screen (score = 0.02827)
An exception has occurred, use %tb to see the full traceback.
頭一次聽說埃及貓：）
3.

comic book (score = 0.11628)動漫書
coffee mug (score = 0.03781)
cup (score = 0.02944)
shower curtain (score = 0.02505)
desktop computer (score = 0.02169)

如果問一個人，這是什麼，大多數回答是一隻貓吧。結果是comic book，看來影象風格(style)對CNN結果有很大影響。
4.

German shepherd, German shepherd dog, German police dog, alsatian (score = 0.95344)德國牧羊犬
malinois (score = 0.00227)
bulletproof vest (score = 0.00115)
bloodhound, sleuthhound (score = 0.00110)
muzzle (score = 0.00071)
經典的樣本！
5.

chow, chow chow (score = 0.82244) 中華田園犬
tabby, tabby cat (score = 0.01480)虎紋貓
Eskimo dog, husky (score = 0.00772)
dingo, warrigal, warragal, Canis dingo (score = 0.00715)
American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier (score = 0.00627)
多個目標的情況，top-1更關注較大的dog？但是top-2的預測表明cat的存在。
6.

gown (score = 0.11101)女禮服，長袍，睡衣
picket fence, paling (score = 0.10401)圍欄
hoopskirt, crinoline (score = 0.10057)裙子
maypole (score = 0.07265)
overskirt (score = 0.06151)

為什麼答案不是一個漂亮的小女孩，而是長裙子，關注點果然不一樣！