简 介： 利用16届智能车竞赛AI视觉组中的动物数据集合，对于百度的 PaddleHub一键动物识别 动物识别模型进行了测试。识别结果是非常令人震惊的。
关键词： Paddle Hub，动物识别
动物识别
文章目录
初步测试
安装paddlehub
显示测试图片
识别结果
识别测试集合
识别代码
狗的识别结果
牛的识别结果
猫的识别结果
马的识别结果
猪的识别结果
识别总结
?
§01 动物识别
??这是在 AI Studio中给出的 PaddleHub一键动物识别 示例程序。
一、初步测试
1、安装paddlehub
??在Notebook中安装 paddlehub。
!pip install paddlehub==1.6.2 -i https://pypi.tuna.tsinghua.edu.cn/simple
2、显示测试图片
test_img_path = ["./1.JPG", "./2.JPG", "./3.JPG"]
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
for imgname in test_img_path:
img1 = mpimg.imread(imgname)
plt.figure(figsize=(10,10))
plt.imshow(img1)
plt.axis('off')
plt.show()
▲ 图1.1.1 大熊猫
▲ 图1.1.2 人脸图片
▲ 图1.1.3 北极狐
3、识别结果
（1）识别代码
#------------------------------------------------------------
import paddlehub as hub
module = hub.Module(name='resnet50_vd_animals')
#------------------------------------------------------------
import cv2
np_images = [cv2.imread(image_path) for image_path in test_img_path]
results = module.classification(images=np_images)
for r in results:
printf(r)
（2）识别种类
{'国宝大熊猫': 0.9751655459403992}
{'非动物': 0.9993972778320312}
{'北极狐': 0.8418184518814087}
二、识别测试集合
1、识别代码
from headm import *
import os
test_img_path = ["./1.JPG", "./2.JPG", "./3.JPG"]
cat_dir = '/home/aistudio/data/fruitanimal'
cat_num = 101
cat_img = [os.path.join(cat_dir, '%02d.jpg'%(i+1)) for i in range(cat_num)]
'''
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
for imgname in cat_img:
img1 = mpimg.imread(imgname)
plt.figure(figsize=(10,10))
plt.imshow(img1)
plt.axis('off')
plt.show()
break
'''
import paddlehub as hub
module = hub.Module(name='resnet50_vd_animals')
import cv2
np_images = [cv2.imread(image_path) for image_path in cat_img]
results = module.classification(images=np_images)
for r in results:
printf(r)
2、狗的识别结果
▲ 图1.2.1 狗的图片
{'日本秋田犬': 0.4390193223953247}
{'贵宾犬/贵妇犬': 0.7055565714836121}
{'金毛犬': 0.8339270949363708}
{'比格猎犬': 0.4970936179161072}
{'德国狐狸犬': 0.5624755620956421}
{'金毛犬': 0.6434336304664612}
{'哈士奇犬': 0.9279824495315552}
{'日本柴犬': 0.7327995896339417}
{'日本柴犬': 0.9790418744087219}
{'哈士奇犬': 0.45240694284439087}
{'威尔士柯基': 0.8236358761787415}
{'八哥犬': 0.9783226251602173}
{'拉布拉多': 0.46611955761909485}
{'拉萨犬': 0.930561363697052}
{'金毛犬': 0.37350478768348694}
{'威尔士柯基': 0.9964550733566284}
{'金毛犬': 0.6246911883354187}
{'吉娃娃犬': 0.5917527079582214}
{'罗秦犬': 0.2610054314136505}
{'威尔士柯基': 0.9904477596282959}
{'中国藏獒': 0.5754819512367249}
{'威尔士柯基': 0.9988589286804199}
{'吉娃娃犬': 0.7712595462799072}
{'法兰西斗牛犬': 0.5187536478042603}
{'八哥犬': 0.9804099202156067}
{'阿拉斯加雪橇犬': 0.7015339732170105}
{'边境牧羊犬': 0.7741223573684692}
{'吉娃娃犬': 0.7257505655288696}
{'爱斯基摩犬': 0.7100096940994263}
{'威尔士柯基': 0.9938674569129944}
{'拳师犬': 0.9122812151908875}
{'金毛犬': 0.7971248030662537}
{'日本柴犬': 0.4854503273963928}
{'阿拉斯加雪橇犬': 0.8994125127792358}
{'边境牧羊犬': 0.8341491222381592}
{'八哥犬': 0.9390298128128052}
{'金毛犬': 0.8075922727584839}
{'八哥犬': 0.9847791790962219}
{'西高地白梗': 0.585416316986084}
{'威尔士柯基': 0.6440405249595642}
{'威尔士柯基': 0.9939017295837402}
{'约克夏梗': 0.9491180181503296}
{'德牧/德国牧羊犬': 0.8708012700080872}
{'贵宾犬/贵妇犬': 0.45029503107070923}
{'日本秋田犬': 0.6675722002983093}
{'塔马斯卡犬': 0.3602724075317383}
{'威尔士柯基': 0.6697006225585938}
{'金毛犬': 0.3383607864379883}
{'美系秋田犬': 0.4068636894226074}
{'德牧/德国牧羊犬': 0.7240146398544312}
{'斯塔福斗牛梗': 0.8090336918830872}
{'拉布拉多': 0.885392427444458}
{'法兰西斗牛犬': 0.975060224533081}
{'威尔士柯基': 0.9927998781204224}
{'威尔士柯基': 0.997052788734436}
{'日本柴犬': 0.43835434317588806}
{'八哥犬': 0.902874231338501}
{'八哥犬': 0.8974903225898743}
{'中华田园犬': 0.6095993518829346}
{'威尔士柯基': 0.9990066885948181}
{'日本柴犬': 0.43599122762680054}
{'八哥犬': 0.9659736752510071}
{'日本柴犬': 0.801028311252594}
{'罗威纳犬': 0.9370702505111694}
{'罗威纳犬': 0.5607684254646301}
{'德牧/德国牧羊犬': 0.964590311050415}
{'法兰西斗牛犬': 0.979912519454956}
{'卷毛比熊犬': 0.8228190541267395}
{'杰克罗素梗': 0.8439692854881287}
{'波士顿梗犬': 0.6153844594955444}
{'卷毛比熊犬': 0.4240884482860565}
{'哈士奇犬': 0.9479284882545471}
{'威尔士柯基': 0.9834445714950562}
{'波士顿梗犬': 0.7555125951766968}
{'马尔济斯犬/玛尔基斯犬': 0.46435272693634033}
{'大麦町': 0.5913124680519104}
{'威尔士柯基': 0.9946886301040649}
{'法兰西斗牛犬': 0.9742651581764221}
{'中华田园犬': 0.6308593153953552}
{'杰克罗素梗': 0.4056360125541687}
{'日本柴犬': 0.6736497282981873}
{'法兰西斗牛犬': 0.9614425301551819}
{'日本柴犬': 0.7812374234199524}
{'非动物': 0.574940025806427}
{'比格猎犬': 0.7072704434394836}
{'拉布拉多': 0.35978037118911743}
{'吉娃娃犬': 0.9188053011894226}
{'腊肠犬': 0.9478339552879333}
{'威尔士柯基': 0.9749516844749451}
{'哈士奇犬': 0.6859499216079712}
{'吉娃娃犬': 0.44198042154312134}
{'圣伯纳犬': 0.9875895380973816}
{'金毛犬': 0.9211183190345764}
{'金毛犬': 0.5072208046913147}
{'哈士奇犬': 0.9294436573982239}
{'哈士奇犬': 0.7804637551307678}
{'比格猎犬': 0.4602883458137512}
{'贵宾犬/贵妇犬': 0.9860490560531616}
{'金毛犬': 0.7351966500282288}
{'拉布拉多': 0.9914411306381226}
{'哈士奇犬': 0.5635216236114502}
3、牛的识别结果
▲ 图1.2.2 牛的图片
{'印度野牛': 0.7731859087944031}
{'和牛': 0.34460482001304626}
{'中国荷斯坦奶牛': 0.4629508852958679}
{'中国荷斯坦奶牛': 0.4254103899002075}
{'中国荷斯坦奶牛': 0.395224004983902}
{'牦牛': 0.729236364364624}
{'湘西黄牛': 0.417185515165329}
{'爪哇野牛': 0.5307871103286743}
{'湘西黄牛': 0.2237340211868286}
{'乳牛': 0.44156643748283386}
{'牦牛': 0.9936890602111816}
{'美洲野牛': 0.5726046562194824}
{'中国荷斯坦奶牛': 0.3730972707271576}
{'中国荷斯坦奶牛': 0.45376989245414734}
{'中国荷斯坦奶牛': 0.3996157646179199}
{'高地牛': 0.9031434655189514}
{'美洲野牛': 0.5250005125999451}
{'水牛': 0.1832694262266159}
{'牦牛': 0.38907766342163086}
{'高地牛': 0.32563480734825134}
{'中国荷斯坦奶牛': 0.4177679419517517}
{'湘西黄牛': 0.19569925963878632}
{'非洲水牛': 0.7169115543365479}
{'高地牛': 0.9156715273857117}
{'印度野牛': 0.793873131275177}
{'南方牛': 0.14685381948947906}
{'湘西黄牛': 0.23747877776622772}
{'湘西黄牛': 0.38618946075439453}
{'牦牛': 0.91637122631073}
{'秦川牛': 0.33473116159439087}
{'湘西黄牛': 0.575921356678009}
{'南方牛': 0.19534429907798767}
{'湘西黄牛': 0.46253302693367004}
{'湘西黄牛': 0.3427804112434387}
{'湘西黄牛': 0.20454934239387512}
{'非洲水牛': 0.3579220175743103}
{'美洲野牛': 0.5778002738952637}
{'和牛': 0.6737017035484314}
{'白牦牛': 0.8647741079330444}
{'麝牛': 0.23257528245449066}
{'牦牛': 0.544623613357544}
{'美洲野牛': 0.5238978862762451}
{'美洲野牛': 0.45008042454719543}
{'湘西黄牛': 0.40401706099510193}
{'麝牛': 0.9536168575286865}
{'非洲水牛': 0.7466286420822144}
{'秦川牛': 0.3693135678768158}
{'非洲水牛': 0.33777937293052673}
{'非洲水牛': 0.3096986711025238}
{'印度野牛': 0.5323782563209534}
{'水牛': 0.3372790813446045}
{'乳牛': 0.3714393675327301}
{'水牛': 0.6502361297607422}
{'水牛': 0.4365774095058441}
{'瑞士褐牛': 0.3834053874015808}
{'牦牛': 0.8131417632102966}
{'湘西黄牛': 0.2282349318265915}
{'乳牛': 0.39998993277549744}
{'水牛': 0.3718227744102478}
{'白牦牛': 0.9743725657463074}
{'牦牛': 0.4934804439544678}
{'印度野牛': 0.6493057608604431}
{'和牛': 0.596123993396759}
{'非洲水牛': 0.6151975989341736}
{'和牛': 0.43248626589775085}
{'乳牛': 0.7132525444030762}
{'瑞士褐牛': 0.33183717727661133}
{'乳牛': 0.422958642244339}
{'湘西黄牛': 0.4469839632511139}
{'水牛': 0.7827041149139404}
{'非洲水牛': 0.10241919010877609}
{'水牛': 0.4067917764186859}
{'犊牛': 0.1201900839805603}
{'牦牛': 0.8989117741584778}
{'瑞士褐牛': 0.16021764278411865}
{'中国荷斯坦奶牛': 0.4101523160934448}
{'印度野牛': 0.5948596596717834}
{'中国荷斯坦奶牛': 0.5168856382369995}
{'德克斯特牛': 0.7600933313369751}
{'非洲水牛': 0.7122604846954346}
{'犊牛': 0.22153298556804657}
{'湘西黄牛': 0.801669180393219}
{'娟珊牛': 0.23559707403182983}
{'湘西黄牛': 0.7210409045219421}
{'野山羊': 0.3539030849933624}
{'水牛': 0.4255494475364685}
{'湘西黄牛': 0.22192026674747467}
{'乳牛': 0.38617074489593506}
{'利木赞牛': 0.2524842321872711}
{'非洲水牛': 0.5881295204162598}
{'美洲野牛': 0.6179811358451843}
{'犊牛': 0.2019311934709549}
{'西门塔尔牛': 0.10599607974290848}
4、猫的识别结果
▲ 图1.2.3 猫的图片
{'家猫': 0.26924195885658264}
{'苏格兰折耳猫': 0.47249680757522583}
{'奶牛猫': 0.48933151364326477}
{'虎斑猫': 0.6846295595169067}
{'土耳其安哥拉猫': 0.16593654453754425}
{'豹猫': 0.6253762245178223}
{'虎斑猫': 0.31445547938346863}
{'红色猫': 0.2440977543592453}
{'土猫': 0.3003983497619629}
{'短毛猫': 0.26512452960014343}
{'虎斑猫': 0.12763258814811707}
{'家猫': 0.3056374192237854}
{'短毛猫': 0.16448454558849335}
{'孟买猫': 0.4597479999065399}
{'曼切堪猫': 0.18091647326946259}
{'奶牛猫': 0.7412574291229248}
{'虎斑猫': 0.1248147115111351}
{'家猫': 0.23250846564769745}
{'家猫': 0.22833330929279327}
{'家猫': 0.25868919491767883}
{'英国短毛猫': 0.549591064453125}
{'短毛猫': 0.3590100109577179}
{'虎斑猫': 0.29695937037467957}
{'土猫': 0.337256520986557}
{'拉格多尔猫': 0.15789814293384552}
{'波斯猫': 0.3578978180885315}
{'美国银色短毛猫': 0.2696826159954071}
{'中华田园猫': 0.8808188438415527}
{'家猫': 0.3876812160015106}
{'家猫': 0.08941750228404999}
{'中华田园猫': 0.0842786356806755}
{'奶牛猫': 0.47373849153518677}
{'日本猫': 0.18907780945301056}
{'西伯利亚猫': 0.254926472902298}
{'苏格兰折耳猫': 0.9196901321411133}
{'科恩家猫': 0.2106335163116455}
{'家猫': 0.21538826823234558}
{'丝毛狗': 0.0697816014289856}
{'英国短毛猫': 0.3487432897090912}
{'虎斑猫': 0.24318566918373108}
{'家猫': 0.4977168142795563}
{'茶杯猫': 0.2898978888988495}
{'短毛猫': 0.488741934299469}
{'美国刚毛猫': 0.18214504420757294}
{'豹猫': 0.45096608996391296}
{'美国短毛猫': 0.3173142373561859}
{'虎斑猫': 0.35126250982284546}
{'英国短毛猫': 0.2422536462545395}
{'家猫': 0.22182634472846985}
{'短毛猫': 0.23754943907260895}
{'短毛猫': 0.4587266743183136}
{'挪威森林猫': 0.3671020567417145}
{'虎斑猫': 0.2662656009197235}
{'家猫': 0.44247087836265564}
{'泰国暹罗猫': 0.6781278252601624}
{'家猫': 0.3432185649871826}
{'俄罗斯蓝猫': 0.289196640253067}
{'虎斑猫': 0.3592875599861145}
{'家猫': 0.6134607791900635}
{'英国短毛猫': 0.38053086400032043}
{'科拉特猫': 0.444489985704422}
{'西伯利亚猫': 0.2271377295255661}
{'英国短毛猫': 0.25782105326652527}
{'美国短毛猫': 0.2770981192588806}
{'虎斑猫': 0.27813711762428284}
{'高地猫': 0.13082613050937653}
{'家猫': 0.3236938714981079}
{'缅因猫': 0.6491696834564209}
{'家猫': 0.28832393884658813}
{'乳黄色猫': 0.4392003118991852}
{'乳黄色猫': 0.3138454556465149}
{'中国狸花猫': 0.5149918794631958}
{'欧洲缅甸猫': 0.522536039352417}
{'英国短毛猫': 0.3905808627605438}
{'折叠猫': 0.2162257730960846}
{'泰国暹罗猫': 0.6795206069946289}
{'雪鞋猫': 0.9029032588005066}
{'家猫': 0.17667511105537415}
{'英国短毛猫': 0.8973835110664368}
{'虎斑猫': 0.3095391094684601}
{'虎斑猫': 0.3123130202293396}
{'纯种猫': 0.18546812236309052}
{'挪威森林猫': 0.5803920030593872}
{'英国短毛猫': 0.5270531177520752}
{'中国狸花猫': 0.3024662733078003}
{'德文帝王猫': 0.2263483703136444}
{'奶牛猫': 0.6385251879692078}
{'虎斑猫': 0.46574538946151733}
{'家猫': 0.23650822043418884}
{'高地猫': 0.4349541664123535}
{'挪威森林猫': 0.8411849141120911}
{'虎斑猫': 0.5040199160575867}
{'英国短毛猫': 0.2173793464899063}
{'粉头斑鸠': 0.386741042137146}
{'美国银色短毛猫': 0.42112547159194946}
{'短毛猫': 0.35389307141304016}
{'美国刚毛猫': 0.43220415711402893}
{'美国刚毛猫': 0.4108104407787323}
{'红色猫': 0.2033773958683014}
5、马的识别结果
▲ 图1.2.4 马的照片
{'骏马': 0.6022858023643494}
{'骏马': 0.950950562953949}
{'骏马': 0.8656469583511353}
{'骏马': 0.6158687472343445}
{'骏马': 0.8990443348884583}
{'骏马': 0.9213634729385376}
{'阿拉伯马': 0.3795621693134308}
{'骏马': 0.41196751594543457}
{'迷你马': 0.3245740234851837}
{'顿河马': 0.4538981020450592}
{'迷你马': 0.5824432373046875}
{'骏马': 0.8510525822639465}
{'伊犁马': 0.30788061022758484}
{'骏马': 0.4718220829963684}
{'骏马': 0.9479358792304993}
{'乌珠穆沁马': 0.7532716393470764}
{'骏马': 0.9822325706481934}
{'骏马': 0.9914455413818359}
{'骏马': 0.818288266658783}
{'骏马': 0.9492048025131226}
{'骏马': 0.5682334899902344}
{'骏马': 0.8446508049964905}
{'骏马': 0.6483210921287537}
{'汗血马': 0.6037880778312683}
{'骏马': 0.9956521391868591}
{'骏马': 0.9248975515365601}
{'骏马': 0.5082840323448181}
{'骏马': 0.6833840012550354}
{'骏马': 0.70458984375}
{'骏马': 0.940241277217865}
{'乌珠穆沁马': 0.5817347764968872}
{'骏马': 0.9363363981246948}
{'骏马': 0.9681546688079834}
{'骏马': 0.7511287927627563}
{'骏马': 0.8071998953819275}
{'汗血马': 0.37583470344543457}
{'骏马': 0.9647538661956787}
{'骏马': 0.36046358942985535}
{'骏马': 0.9946079254150391}
{'骏马': 0.9076221585273743}
{'骏马': 0.9875245094299316}
{'骏马': 0.9982917904853821}
{'骏马': 0.9535431265830994}
{'骏马': 0.9513123035430908}
{'骏马': 0.9874684810638428}
{'骏马': 0.846973180770874}
{'骏马': 0.7147549390792847}
{'骏马': 0.49888062477111816}
{'骏马': 0.9786887168884277}
{'汗血马': 0.43537816405296326}
{'骏马': 0.9652038812637329}
{'阿拉伯马': 0.5125514268875122}
{'骏马': 0.5014575123786926}
{'骏马': 0.5922220945358276}
{'骏马': 0.9749410152435303}
{'骏马': 0.8920226693153381}
{'骏马': 0.9516306519508362}
{'骏马': 0.9608860015869141}
{'顿河马': 0.44896700978279114}
{'骏马': 0.956926703453064}
{'骏马': 0.8580583930015564}
{'骏马': 0.8942516446113586}
{'骏马': 0.9149570465087891}
{'骏马': 0.978945791721344}
{'骏马': 0.9947801828384399}
{'矮种马': 0.4738619923591614}
{'骏马': 0.9139372706413269}
{'骏马': 0.9015092253684998}
{'骏马': 0.9814856648445129}
{'骏马': 0.457716166973114}
{'顿河马': 0.3433278501033783}
{'阿帕卢萨马': 0.3573785424232483}
{'骏马': 0.8493509888648987}
{'骏马': 0.9699633717536926}
{'骏马': 0.8633155822753906}
{'骏马': 0.41833093762397766}
{'骏马': 0.9849001169204712}
{'乌珠穆沁马': 0.9263110756874084}
{'骏马': 0.9967548251152039}
{'骏马': 0.6996698975563049}
{'骏马': 0.8943467736244202}
{'骏马': 0.6823334693908691}
{'骏马': 0.6819928884506226}
{'骏马': 0.9621237516403198}
{'骏马': 0.9680446982383728}
{'骏马': 0.9633324146270752}
{'骏马': 0.9864280819892883}
{'骏马': 0.9445153474807739}
{'顿河马': 0.40485844016075134}
{'骏马': 0.758404016494751}
{'骏马': 0.5660824179649353}
{'蒙古马': 0.3801785707473755}
{'骏马': 0.5563110113143921}
{'骏马': 0.4901660680770874}
{'骏马': 0.9210300445556641}
6、猪的识别结果
▲ 图1.2.5 猪的照片
{'家猪': 0.5635786056518555}
{'香猪': 0.5747232437133789}
{'长白猪': 0.34550777077674866}
{'种猪': 0.32950359582901}
{'小香猪': 0.4352666139602661}
{'家猪': 0.7468473315238953}
{'家猪': 0.7181001901626587}
{'小香猪': 0.5445407032966614}
{'种猪': 0.45520180463790894}
{'家猪': 0.4995124340057373}
{'香猪': 0.38358211517333984}
{'香猪': 0.6193317174911499}
{'家猪': 0.37872937321662903}
{'二元母猪': 0.49666938185691833}
{'家猪': 0.7282549738883972}
{'种猪': 0.8240048289299011}
{'北京黑猪': 0.6791740655899048}
{'北京黑猪': 0.4441528916358948}
{'种猪': 0.921556293964386}
{'黑山猪': 0.3642032742500305}
{'种猪': 0.881543755531311}
{'家猪': 0.5777103304862976}
{'二元母猪': 0.49592897295951843}
{'香猪': 0.6794046759605408}
{'北京黑猪': 0.3254739046096802}
{'家猪': 0.5590469837188721}
{'从江香猪': 0.37327274680137634}
{'家猪': 0.7930817604064941}
{'种猪': 0.49385035037994385}
{'香猪': 0.13682734966278076}
{'从江香猪': 0.52841717004776}
{'种猪': 0.5118933320045471}
{'家猪': 0.596570611000061}
{'从江香猪': 0.3684907853603363}
{'二元母猪': 0.682600736618042}
{'宠物猪': 0.2680521607398987}
{'家猪': 0.32175758481025696}
{'家猪': 0.7427680492401123}
{'特种野猪': 0.6692291498184204}
{'家猪': 0.5245686173439026}
{'种猪': 0.6978824138641357}
{'家猪': 0.7604533433914185}
{'黑山猪': 0.4341350197792053}
{'宠物猪': 0.6151537895202637}
{'种猪': 0.5130553245544434}
{'香猪': 0.5160796046257019}
{'特种野猪': 0.4091901183128357}
{'宠物猪': 0.8739631175994873}
{'二元母猪': 0.41864296793937683}
{'宠物猪': 0.48659852147102356}
{'宠物猪': 0.6616140604019165}
{'家猪': 0.38524940609931946}
{'种猪': 0.7332367897033691}
{'种猪': 0.3837487995624542}
{'小香猪': 0.4615360498428345}
{'种猪': 0.548019528388977}
{'黑山猪': 0.19770154356956482}
{'宠物猪': 0.473903089761734}
{'宠物猪': 0.5246024131774902}
{'北京黑猪': 0.5247050523757935}
{'北京黑猪': 0.26427027583122253}
{'香猪': 0.5340824723243713}
{'二元母猪': 0.24352841079235077}
{'家猪': 0.6880110502243042}
{'家猪': 0.3890184164047241}
{'种猪': 0.4581379294395447}
{'从江香猪': 0.23529388010501862}
{'北京黑猪': 0.5662075877189636}
{'种猪': 0.3733404278755188}
{'种猪': 0.46214601397514343}
{'宠物猪': 0.7731081247329712}
{'汉普夏猪': 0.4764883518218994}
{'北京黑猪': 0.5394860506057739}
{'种猪': 0.34310197830200195}
{'家猪': 0.4950934052467346}
{'宠物猪': 0.494595468044281}
{'家猪': 0.4026821255683899}
{'家猪': 0.3686463534832001}
{'家猪': 0.5061211585998535}
{'黑山猪': 0.404338002204895}
{'西猯': 0.39404913783073425}
{'荣昌猪': 0.5950074195861816}
{'西猯': 0.42875492572784424}
{'家猪': 0.4807981252670288}
{'家猪': 0.6012528538703918}
{'家猪': 0.816167414188385}
{'家猪': 0.6905205845832825}
{'小香猪': 0.4659614562988281}
?
※ 识别总结 ※
??利用16届智能车竞赛AI视觉组中的动物数据集合，对于百度的 PaddleHub一键动物识别 动物识别模型进行了测试。识别结果是非常令人震惊的。
■ 相关文献链接:
● 相关图表链接:
#!/usr/local/bin/python
# -*- coding: gbk -*-
#============================================================
# TESTANIMAL.PY -- by Dr. ZhuoQing 2021-12-10
#
# Note:
#============================================================
from headm import *
import os
test_img_path = ["./1.JPG", "./2.JPG", "./3.JPG"]
cat_dir = '/home/aistudio/data/fruitanimal'
cow_dir = '/home/aistudio/data/fruitanimal/cow'
cat_dir = '/home/aistudio/data/fruitanimal/cat'
horse_dir = '/home/aistudio/data/fruitanimal/horse'
pig_dir = '/home/aistudio/data/fruitanimal/pig'
cat_num = 101
cow_num = 93
cat_num = 99
horse_num = 95
pig_num = 88
cat_img = [os.path.join(cat_dir, '%02d.jpg'%(i+1)) for i in range(cat_num)]
cow_img = [os.path.join(cow_dir, '%d.png'%(i+1)) for i in range(cow_num)]
cat_img = [os.path.join(cat_dir, '%02d.png'%(i+1)) for i in range(cat_num)]
horse_img = [os.path.join(horse_dir, '%02d.png'%(i+1)) for i in range(horse_num)]
pig_img = [os.path.join(pig_dir, '%02d.png'%(i+1)) for i in range(pig_num)]
#print(cat_img)
#------------------------------------------------------------
'''
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
for imgname in cat_img:
img1 = mpimg.imread(imgname)
plt.figure(figsize=(10,10))
plt.imshow(img1)
plt.axis('off')
plt.show()
break
'''
#------------------------------------------------------------
import paddlehub as hub
module = hub.Module(name='resnet50_vd_animals')
#------------------------------------------------------------
import cv2
np_images = [cv2.imread(image_path) for image_path in pig_img if os.path.isfile(image_path)]
#printf(np_images)
results = module.classification(images=np_images)
for r in results:
printf(r)
#------------------------------------------------------------
# END OF FILE : TESTANIMAL.PY
#============================================================