Tensorflow 和 Keras 除了能处理[前一篇](https://busy.org/@hongtao/tensorflow-keras)文章提到的回归(Regression,拟合&预测)的问题之外,还可以处理分类(Classfication)的问题。 这篇文章我们就介绍一下如何用Keras快速搭建一个线性分类器或神经网络,通过分析病人的生理数据来判断这个人是否患有糖尿病。 同样的,为了方便与读者交流,所有的源代码都放在了这里: https://github.com/zht007/tensorflow-practice ### 1. 数据的导入 数据的csv文件已经放在了项目目录中,也可以去[Kaggle](https://www.kaggle.com/uciml/pima-indians-diabetes-database)下载。  ### 2.数据预处理 #### 2.1 Normalization(标准化)数据 标准化数据可以用sklearn的工具,但我这里就直接计算了。要注意的是,这里没有标准化年龄。 ```python cols_to_norm = ['Number_pregnant', 'Glucose_concentration', 'Blood_pressure', 'Triceps', 'Insulin', 'BMI', 'Pedigree'] diabetes[cols_to_norm] = diabetes[cols_to_norm].apply(lambda x: (x - x.min()) / (x.max() - x.min())) ``` #### 2.2 年龄分段 对于向年龄这样的数据,通常需要按年龄段进行分类,我们先看看数据中的年龄构成。  可以通过panda自带的cut函数对年龄进行分段,我们这里将年龄分成0-30,30-50,50-70,70-100四段,分别标记为0,1,2,3 ```python bins = [0,30,50,70,100] labels =[0,1,2,3] diabetes["Age_buckets"] = pd.cut(diabetes["Age"],bins=bins, labels=labels, include_lowest=True) ``` #### 3.4 训练和测试分组 这一步不用多说,还是用sklearn.model_selection 的 train_test_split工具进行处理。 ```python from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(x_data,labels,test_size=0.33, random_state=101) ``` ### 3. 用Keras搭建线性分类器 与[前一篇](https://busy.org/@hongtao/tensorflow-keras)文章中介绍的线性回归模型一样,但线性分类器输出的Unit 为 2 需要加一个"sorftmax"的激活函数。 ```python from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense,Activation from tensorflow.keras.optimizers import SGD,Adam from tensorflow.keras.utils import to_categorical model = Sequential() model.add(Dense(2,input_shape = (X_train.shape[1],),activation = 'softmax')) ``` 需要注意的是标签y需要进行转换,实际上是将一元数据转换成二元数据(Binary)的"One Hot"数据。比如原始标签用"[1]"和"[0]"这样的一元标签来标记"是"“否”患病,转换之后是否患病用"[1 , 0]"和"[0 , 1]"这样的二元标签来标记。 ```python y_binary_train= to_categorical(y_train) y_binary_test = to_categorical(y_test) ``` 同样可以选用SGD的优化器,但是要注意的是,在Compile的时候损失函数要选择"categorical_crossentropy" ```python sgd = SGD(0.005) model.compile(loss = 'categorical_crossentropy', optimizer = sgd, metrics=['accuracy']) ``` ### 4. 分类器的训练 训练的时候可以直接将测试数据带入,以方便评估训练效果。 ```python H = model.fit(X_train, y_binary_train, validation_data=(X_test, y_binary_test),epochs = 500) ``` ### 5. 训练效果验证 训练效果可以直接调用history查看损失函数和准确率的变化轨迹,线性分类器的效果还不错。  ### 6. 改用神经网络试试 这里我在model中搭建一个20x10的两层全连接的神经网络,优化器选用adam ```python model = Sequential() model.add(Dense(20,input_shape = (X_train.shape[1],), activation = 'relu')) model.add(Dense(10,activation = 'relu')) model.add(Dense(2, activation = 'softmax')) adam = Adam(0.01) ``` 可以看到,虽然精确度比采用线性分类器稍高,但是在200个epoch之后,明显出现过拟合(Over fitting)的现象。  ### 7. 用模型进行预测 同样的我们可以用训练得到的模型对验证数据进行预测,这里需要注意的是我们最后需要将二元数据用np.argmax转换成一元数据。 ```python import numpy as np y_pred_softmax = model.predict(X_test) y_pred = np.argmax(y_pred_softmax, axis=1) ``` --- 同步到我的简书 https://www.jianshu.com/u/bd506afc6fc1
author | hongtao | ||||||
---|---|---|---|---|---|---|---|
permlink | tensorflow-keras-classification-with-keras | ||||||
category | cn-stem | ||||||
json_metadata | {"community":"busy","app":"steemit/0.1","format":"markdown","tags":["cn-stem","tensorflow","keras","team-cn","busy"],"links":["https://busy.org/@hongtao/tensorflow-keras","https://github.com/zht007/tensorflow-practice","https://www.kaggle.com/uciml/pima-indians-diabetes-database","https://www.jianshu.com/u/bd506afc6fc1"],"image":["https://ws3.sinaimg.cn/large/006tKfTcgy1g15est7xhdj31540f80v5.jpg","https://ws2.sinaimg.cn/large/006tKfTcgy1g15f5pmw97j30qu0lwac5.jpg","https://ws1.sinaimg.cn/large/006tKfTcgy1g15g21e2p5j30oy0jc0v8.jpg","https://ws4.sinaimg.cn/large/006tKfTcgy1g15g8670u8j30og0jc43p.jpg"]} | ||||||
created | 2019-03-16 23:55:54 | ||||||
last_update | 2019-03-20 10:25:09 | ||||||
depth | 0 | ||||||
children | 2 | ||||||
last_payout | 2019-03-23 23:55:54 | ||||||
cashout_time | 1969-12-31 23:59:59 | ||||||
total_payout_value | 1.950 HBD | ||||||
curator_payout_value | 0.662 HBD | ||||||
pending_payout_value | 0.000 HBD | ||||||
promoted | 0.000 HBD | ||||||
body_length | 3,186 | ||||||
author_reputation | 3,241,267,862,629 | ||||||
root_title | "Tensorflow入门——Keras处理分类问题,Classification with Keras" | ||||||
beneficiaries |
| ||||||
max_accepted_payout | 1,000,000.000 HBD | ||||||
percent_hbd | 10,000 | ||||||
post_id | 81,431,717 | ||||||
net_rshares | 4,220,557,708,134 | ||||||
author_curate_reward | "" |
voter | weight | wgt% | rshares | pct | time |
---|---|---|---|---|---|
wackou | 0 | 81,155,919,577 | 1.29% | ||
tombstone | 0 | 202,240,824,045 | 0.86% | ||
delegate.lafona | 0 | 241,673,825,923 | 20% | ||
lola-carola | 0 | 362,318,443 | 2.16% | ||
kevinwong | 0 | 40,545,615,875 | 0.5% | ||
eric-boucher | 0 | 7,241,389,574 | 2.16% | ||
anwenbaumeister | 0 | 187,641,268 | 4.32% | ||
norbu | 0 | 46,650,576,546 | 50% | ||
diana.catherine | 0 | 10,444,395,837 | 50% | ||
liberosist | 0 | 1,487,553,168 | 4.32% | ||
arconite | 0 | 102,397,023 | 0.25% | ||
psygambler | 0 | 251,213,721 | 2.16% | ||
lemouth | 0 | 50,218,384,311 | 10% | ||
rwilday | 0 | 57,258,668 | 100% | ||
lamouthe | 0 | 11,297,107,805 | 20% | ||
lk666 | 0 | 733,575,414 | 2.16% | ||
justyy | 0 | 52,888,615,841 | 2.21% | ||
whoib | 0 | 682,718,895 | 70% | ||
curie | 0 | 1,352,635,313,792 | 4.32% | ||
hendrikdegrote | 0 | 55,471,040,891 | 4.32% | ||
vact | 0 | 82,430,600,711 | 4.32% | ||
steemstem | 0 | 811,867,607,496 | 20% | ||
dashfit | 0 | 360,051,739 | 2.16% | ||
gangstayid | 0 | 97,976,023 | 2.16% | ||
busy.org | 0 | 27,407,662 | 0.3% | ||
vodonik | 0 | 80,168,918 | 6.6% | ||
dna-replication | 0 | 5,644,197,583 | 20% | ||
gmedley | 0 | 315,598,033 | 2.16% | ||
diebaasman | 0 | 2,417,727,779 | 12% | ||
moksamol | 0 | 515,331,388 | 2.16% | ||
getrichordie | 0 | 144,181,034 | 2.16% | ||
thatsweeneyguy | 0 | 101,972,691 | 2.16% | ||
szokerobert | 0 | 116,851,532 | 0.86% | ||
bloom | 0 | 79,289,946,488 | 20% | ||
eurogee | 0 | 131,415,266 | 2% | ||
iansart | 0 | 1,400,273,521 | 2.16% | ||
kryzsec | 0 | 846,182,461 | 16% | ||
jiujitsu | 0 | 1,836,007,909 | 2.16% | ||
lekang | 0 | 586,105,434 | 2.16% | ||
improv | 0 | 2,853,491,899 | 11% | ||
helo | 0 | 21,638,744,522 | 10% | ||
samminator | 0 | 7,994,948,147 | 10% | ||
isacoin | 0 | 5,080,411,329 | 15% | ||
locikll | 0 | 2,603,607,246 | 8.64% | ||
kjaeger | 0 | 60,845,006 | 50% | ||
mahdiyari | 0 | 17,008,400,132 | 10% | ||
lorenzor | 0 | 5,382,511,920 | 50% | ||
aboutyourbiz | 0 | 798,863,053 | 4.32% | ||
alexander.alexis | 0 | 9,649,121,519 | 20% | ||
howtostartablog | 0 | 88,459,655 | 0.43% | ||
jonmagnusson | 0 | 145,253,760 | 1.08% | ||
suesa | 0 | 98,038,169,912 | 25% | ||
cryptokrieg | 0 | 772,283,264 | 4.32% | ||
rival | 0 | 1,946,886,952 | 2% | ||
slickhustler007 | 0 | 169,321,791 | 2.16% | ||
corsica | 0 | 8,343,594,849 | 20% | ||
makrotheblack | 0 | 96,859,695 | 2.16% | ||
flatman | 0 | 958,921,816 | 4.32% | ||
allcapsonezero | 0 | 2,129,318,446 | 2.16% | ||
howo | 0 | 55,489,682,510 | 10% | ||
tsoldovieri | 0 | 1,452,851,283 | 10% | ||
nitego | 0 | 497,773,876 | 1.29% | ||
hotsteam | 0 | 3,452,672,155 | 10% | ||
neumannsalva | 0 | 590,807,377 | 2.16% | ||
wargof | 0 | 192,415,252 | 10% | ||
abigail-dantes | 0 | 340,806,144,873 | 20% | ||
phogyan | 0 | 87,358,745 | 2.16% | ||
esteemguy | 0 | 165,513,488 | 20% | ||
zonguin | 0 | 1,261,112,504 | 5% | ||
g0nr0gue | 0 | 76,881,524 | 2.16% | ||
alexzicky | 0 | 5,536,255,386 | 5% | ||
mountain.phil28 | 0 | 3,198,556,411 | 25% | ||
jasonbu | 0 | 10,050,837,699 | 25% | ||
thehulk07 | 0 | 463,229,153 | 2.16% | ||
coolbuddy | 0 | 0 | 1% | ||
muliadi | 0 | 63,663,390 | 2.16% | ||
stinawog | 0 | 229,776,066 | 11% | ||
tuoficinavirtual | 0 | 75,479,373 | 25% | ||
tanyaschutte | 0 | 79,393,327 | 2% | ||
kingswisdom | 0 | 79,910,059 | 10% | ||
zest | 0 | 3,657,884,380 | 10% | ||
felixrodriguez | 0 | 1,063,123,886 | 10% | ||
azulear | 0 | 450,737,853 | 100% | ||
psicoluigi | 0 | 296,894,534 | 50% | ||
vadimlasca | 0 | 79,077,464 | 4.32% | ||
mr-aaron | 0 | 104,291,426 | 10% | ||
eurodale | 0 | 177,852,647 | 2.16% | ||
reaverza | 0 | 1,264,737,201 | 15% | ||
clweeks | 0 | 230,935,467 | 2.59% | ||
osm0sis | 0 | 7,520,445,859 | 11% | ||
superbing | 0 | 749,314,483 | 7.64% | ||
dokter-purnama | 0 | 260,253,913 | 2.16% | ||
infamousit | 0 | 4,129,104,268 | 25% | ||
erikkun28 | 0 | 0 | 1% | ||
dailystats | 0 | 2,248,864,202 | 7.63% | ||
jlsplatts | 0 | 188,498,571 | 0.64% | ||
mayowadavid | 0 | 860,896,175 | 10% | ||
poodai | 0 | 148,755,326 | 2.16% | ||
markmorbidity | 0 | 100,382,512 | 2.16% | ||
emdesan | 0 | 140,036,510 | 10% | ||
peaceandwar | 0 | 620,855,460 | 2.16% | ||
enzor | 0 | 246,086,213 | 10% | ||
joendegz | 0 | 92,994,985 | 2.16% | ||
florian-glechner | 0 | 95,470,246 | 0.43% | ||
carlos84 | 0 | 5,614,498,150 | 100% | ||
gra | 0 | 7,640,785,268 | 20% | ||
jianan | 0 | 1,471,120,264 | 8.34% | ||
shayekh2 | 0 | 105,778,649 | 50% | ||
agbona | 0 | 113,243,102 | 5% | ||
ykdesign | 0 | 316,355,569 | 2.16% | ||
pinksteam | 0 | 1,137,460,509 | 10% | ||
aalok | 0 | 87,705,305 | 26% | ||
nicole-st | 0 | 426,218,187 | 2.16% | ||
teukurival | 0 | 161,649,106 | 2.16% | ||
drmake | 0 | 2,326,312,871 | 2.16% | ||
anxin | 0 | 171,030,729 | 8.57% | ||
guga34 | 0 | 475,942,785 | 15% | ||
amestyj | 0 | 2,314,401,699 | 50% | ||
sandracarrascal | 0 | 401,521,982 | 100% | ||
skycae | 0 | 532,070,974 | 4.32% | ||
zapncrap | 0 | 8,506,111,911 | 11% | ||
xanderslee | 0 | 203,794,720 | 4.32% | ||
egotheist | 0 | 192,855,642 | 2% | ||
kenadis | 0 | 4,577,510,687 | 20% | ||
esaia.mystic | 0 | 156,158,859 | 4.32% | ||
maticpecovnik | 0 | 2,922,806,481 | 8% | ||
robotics101 | 0 | 2,003,165,784 | 20% | ||
tristan-muller | 0 | 80,198,661 | 20% | ||
gentleshaid | 0 | 7,912,988,505 | 10% | ||
thescubageek | 0 | 220,055,223 | 2.16% | ||
fejiro | 0 | 213,364,700 | 10% | ||
danaedwards | 0 | 320,070,833 | 4.32% | ||
ivymalifred | 0 | 1,764,841,787 | 50% | ||
sco | 0 | 17,634,983,033 | 20% | ||
douglimarbalzan | 0 | 367,838,876 | 100% | ||
ennyta | 0 | 796,973,675 | 50% | ||
hkmoon | 0 | 82,114,951 | 2.16% | ||
rharphelle | 0 | 636,986,697 | 25% | ||
stahlberg | 0 | 928,983,371 | 2.16% | ||
gabrielatravels | 0 | 186,345,713 | 1.08% | ||
cordeta | 0 | 75,992,723 | 2.16% | ||
reizak | 0 | 334,100,315 | 1.72% | ||
zlatkamrs | 0 | 214,764,345 | 4.1% | ||
monie | 0 | 387,546,772 | 100% | ||
creatrixity | 0 | 57,647,213 | 2.16% | ||
eliaschess333 | 0 | 8,638,171,965 | 50% | ||
shoganaii | 0 | 185,799,686 | 10% | ||
darkiche | 0 | 76,730,472 | 10% | ||
ydavgonzalez | 0 | 1,164,816,008 | 5% | ||
payger | 0 | 128,556,587 | 2.16% | ||
langford | 0 | 354,749,794 | 20% | ||
mattiarinaldoni | 0 | 0 | 1% | ||
mathowl | 0 | 4,319,067,334 | 10% | ||
shinedojo | 0 | 377,372,295 | 4.32% | ||
hongtao | 0 | 188,195,047 | 60% | ||
gaming.yer | 0 | 403,365,292 | 100% | ||
curx | 0 | 7,730,171,619 | 11% | ||
steem-familia | 0 | 402,044,940 | 100% | ||
lacher-prise | 0 | 190,612,519 | 10% | ||
terrylovejoy | 0 | 3,622,755,421 | 8% | ||
jcalero | 0 | 136,971,014 | 4.32% | ||
wisewoof | 0 | 117,795,253 | 2.16% | ||
vilda | 0 | 161,385,107 | 50% | ||
neneandy | 0 | 4,732,833,721 | 4.32% | ||
olajidekehinde | 0 | 81,822,455 | 10% | ||
real2josh | 0 | 153,135,951 | 10% | ||
steepup | 0 | 274,998,588 | 8% | ||
reavercois | 0 | 0 | 5% | ||
gribouille | 0 | 489,651,029 | 20% | ||
traviseric | 0 | 158,354,153 | 50% | ||
woolfe19861008 | 0 | 139,577,329 | 8.57% | ||
yrmaleza | 0 | 342,152,277 | 50% | ||
stemng | 0 | 6,617,502,941 | 10% | ||
mininthecity | 0 | 151,859,438 | 3.45% | ||
edprivat | 0 | 1,874,014,830 | 0.15% | ||
grizzle | 0 | 76,338,803 | 1% | ||
trixie | 0 | 72,979,877 | 10% | ||
kingabesh | 0 | 508,447,441 | 10% | ||
evangelista.yova | 0 | 398,151,771 | 100% | ||
miguelangel2801 | 0 | 721,401,728 | 50% | ||
dailychina | 0 | 2,131,047,623 | 7.65% | ||
didic | 0 | 2,546,154,801 | 2.16% | ||
jenniferjulieth | 0 | 363,311,182 | 100% | ||
operahoser | 0 | 202,865,062 | 0.64% | ||
emiliomoron | 0 | 3,414,529,878 | 50% | ||
dexterdev | 0 | 3,110,336,468 | 10% | ||
intellihandling | 0 | 2,264,932,711 | 50% | ||
nwjordan | 0 | 570,085,315 | 4.32% | ||
oghie | 0 | 625,523,987 | 50% | ||
geopolis | 0 | 1,284,642,631 | 20% | ||
ajfernandez | 0 | 345,989,155 | 100% | ||
dongfengman | 0 | 866,092,029 | 8.57% | ||
robertbira | 0 | 2,068,319,080 | 5% | ||
bearded-benjamin | 0 | 60,587,984,122 | 50% | ||
atomcollector | 0 | 3,319,136,341 | 20% | ||
alexdory | 0 | 3,954,401,882 | 8% | ||
flugschwein | 0 | 4,649,342,697 | 19% | ||
benleemusic | 0 | 310,658,432 | 0.43% | ||
francostem | 0 | 2,714,101,162 | 20% | ||
ivan-g | 0 | 519,861,727 | 2.16% | ||
endopediatria | 0 | 693,858,767 | 20% | ||
tajstar | 0 | 59,665,066 | 100% | ||
croctopus | 0 | 1,441,099,302 | 100% | ||
zipporah | 0 | 889,699,485 | 0.86% | ||
sissyjill | 0 | 77,421,400 | 7% | ||
ingmarvin | 0 | 371,675,883 | 100% | ||
emmanuel293 | 0 | 83,013,999 | 25% | ||
cryptofuwealth | 0 | 41,141,352 | 11% | ||
djoi | 0 | 372,149,781 | 5% | ||
ethanlee | 0 | 220,645,657 | 7% | ||
morbyjohn | 0 | 136,395,560 | 7% | ||
alix96 | 0 | 363,456,611 | 100% | ||
ambitiouslife | 0 | 234,397,180 | 2.16% | ||
tomastonyperez | 0 | 10,189,295,652 | 50% | ||
jingis07 | 0 | 398,448,297 | 2.16% | ||
elvigia | 0 | 8,489,481,846 | 50% | ||
scoora82 | 0 | 934,274,371 | 24% | ||
qberry | 0 | 2,050,315,723 | 2.16% | ||
gabyoraa | 0 | 97,828,450 | 2.16% | ||
lesmouths-travel | 0 | 976,506,185 | 13% | ||
kentonlee | 0 | 267,557,028 | 75% | ||
cjunros | 0 | 94,636,696 | 2.16% | ||
effofex | 0 | 2,172,717,345 | 10% | ||
luiscd8a | 0 | 1,518,437,281 | 80% | ||
lilypang22 | 0 | 191,963,173 | 7.76% | ||
eniolw | 0 | 343,049,876 | 5% | ||
de-stem | 0 | 7,582,967,183 | 19.8% | ||
elsll | 0 | 94,626,736 | 4.32% | ||
elpdl | 0 | 421,439,230 | 100% | ||
derbesserwisser | 0 | 1,816,393,320 | 100% | ||
serylt | 0 | 3,374,228,655 | 19.6% | ||
bavi | 0 | 117,749,805 | 2.16% | ||
hiddenblade | 0 | 1,566,043,306 | 3.45% | ||
josedelacruz | 0 | 4,578,992,892 | 50% | ||
joseangelvs | 0 | 1,832,995,749 | 100% | ||
viannis | 0 | 1,458,352,733 | 50% | ||
flores39 | 0 | 373,439,315 | 100% | ||
majapesi | 0 | 228,407,666 | 50% | ||
michaelwrites | 0 | 229,567,867 | 10% | ||
deholt | 0 | 941,279,540 | 20% | ||
archaimusic | 0 | 118,369,917 | 10% | ||
smacommunity | 0 | 154,150,088 | 2.16% | ||
musicvoter | 0 | 3,385,013,614 | 1% | ||
goodway | 0 | 140,369,781 | 1% | ||
nigerian-yogagal | 0 | 70,529,319 | 2.16% | ||
stevenwood | 0 | 79,554,566 | 2.16% | ||
temitayo-pelumi | 0 | 1,496,237,834 | 20% | ||
andrick | 0 | 402,486,737 | 50% | ||
sweet-jenny8 | 0 | 1,687,724,804 | 8.56% | ||
yusvelasquez | 0 | 433,856,849 | 50% | ||
doctor-cog-diss | 0 | 309,178,315 | 20% | ||
alexworld | 0 | 264,381,186 | 25% | ||
gracelbm | 0 | 200,908,258 | 2.16% | ||
avizor | 0 | 63,580,224 | 2.16% | ||
acont | 0 | 228,694,399 | 50% | ||
niouton | 0 | 177,416,867 | 0.86% | ||
purelove | 0 | 70,179,053 | 20% | ||
elimao | 0 | 367,812,053 | 100% | ||
schroders | 0 | 1,630,529,026 | 1.29% | ||
anaestrada12 | 0 | 16,108,170,234 | 100% | ||
hardaeborla | 0 | 132,504,398 | 2.16% | ||
steemzeiger | 0 | 1,068,868,125 | 19.8% | ||
yorgermadison | 0 | 327,516,053 | 100% | ||
alexjunior | 0 | 338,856,594 | 100% | ||
faiyazmahmud | 0 | 1,893,332,543 | 35% | ||
somegaming | 0 | 93,718,039 | 4.32% | ||
antunez25 | 0 | 367,741,411 | 100% | ||
haf67 | 0 | 344,230,065 | 100% | ||
joelsegovia | 0 | 3,384,611,075 | 50% | ||
chavas | 0 | 384,832,342 | 100% | ||
longer | 0 | 213,914,550 | 50% | ||
kafupraise | 0 | 86,258,341 | 34% | ||
biomimi | 0 | 140,641,373 | 40% | ||
ibk-gabriel | 0 | 121,868,651 | 10% | ||
drsensor | 0 | 1,447,871,249 | 8% | ||
mirzantorres | 0 | 247,827,493 | 50% | ||
hhtb | 0 | 168,161,312 | 2.16% | ||
angelica7 | 0 | 669,844,476 | 0.21% | ||
ilovecryptopl | 0 | 570,943,720 | 3.45% | ||
purelyscience | 0 | 117,631,595 | 10% | ||
eglinson | 0 | 318,072,855 | 100% | ||
uzcateguiazambra | 0 | 376,030,756 | 100% | ||
yomismosoy | 0 | 253,936,864 | 50% | ||
casiloko | 0 | 167,236,696 | 50% | ||
bflanagin | 0 | 311,093,470 | 2.16% | ||
asmeira | 0 | 407,486,495 | 100% | ||
garrillo | 0 | 321,818,967 | 100% | ||
lillywilton | 0 | 653,085,368 | 20% | ||
yestermorrow | 0 | 1,850,397,426 | 6% | ||
mary11 | 0 | 353,816,943 | 75% | ||
laiyuehta | 0 | 86,114,787 | 4.96% | ||
hansmast | 0 | 314,077,546 | 2.16% | ||
turtlegraphics | 0 | 709,444,011 | 7.63% | ||
wstanley226 | 0 | 93,525,201 | 50% | ||
gpcx86 | 0 | 733,623,158 | 25% | ||
andypalacios | 0 | 205,050,475 | 50% | ||
reinaseq | 0 | 6,149,255,001 | 100% | ||
p4ragon | 0 | 1,437,724,596 | 50% | ||
yaelg | 0 | 2,513,093,593 | 5% | ||
pfernandezpetit | 0 | 329,200,933 | 100% | ||
mgarrillogonzale | 0 | 352,419,918 | 100% | ||
rubenp | 0 | 421,847,350 | 100% | ||
jeferc | 0 | 418,987,416 | 100% | ||
steeming-hot | 0 | 0 | 0.02% | ||
clement.poiret | 0 | 227,096,931 | 4.32% | ||
ogsenti | 0 | 70,341,552 | 100% | ||
fran.frey | 0 | 1,660,721,995 | 50% | ||
emsteemians | 0 | 101,785,071 | 10% | ||
perpetuum-lynx | 0 | 413,184,208 | 19.6% | ||
jrevilla | 0 | 317,652,290 | 50% | ||
annaabi | 0 | 284,678,313 | 2.16% | ||
emperorhassy | 0 | 134,980,323 | 10% | ||
moniroy | 0 | 2,697,404,064 | 50% | ||
skorup87 | 0 | 16,167,643 | 11% | ||
meq | 0 | 817,117,253 | 100% | ||
trang | 0 | 375,878,415 | 2.16% | ||
stem-espanol | 0 | 54,971,248,877 | 100% | ||
praditya | 0 | 463,581,197 | 24% | ||
rishhk | 0 | 70,152,827 | 15% | ||
gbemy | 0 | 70,224,815 | 20% | ||
rhethypo | 0 | 106,570,399 | 2.16% | ||
predict-crypto | 0 | 94,657,677 | 0.08% | ||
javier.dejuan | 0 | 4,764,313,496 | 20% | ||
witnesstools | 0 | 682,678,566 | 7.63% | ||
sciencetech | 0 | 143,899,894 | 2% | ||
hirally | 0 | 376,424,815 | 100% | ||
emynb | 0 | 323,745,837 | 100% | ||
fanta-steem | 0 | 1,559,442,949 | 30% | ||
desikaamukkahani | 0 | 91,708,699 | 4.32% | ||
reverseacid | 0 | 189,099,437 | 2.16% | ||
giulyfarci52 | 0 | 959,936,179 | 50% | ||
semtroneum | 0 | 83,622,220 | 1.29% | ||
eu-id | 0 | 629,241,328 | 10% | ||
ilovecoding | 0 | 677,534,488 | 7.63% | ||
alvin0617 | 0 | 243,242,326 | 2.16% | ||
sbdpayback | 0 | 49,009,519 | 100% | ||
stem.witness | 0 | 14,014,110,707 | 20% | ||
sarhugo | 0 | 119,730,759 | 2.16% | ||
cheddarsfloss | 0 | 485,620,276 | 100% | ||
sillyboast | 0 | 485,792,003 | 100% | ||
meetingsnazzy | 0 | 485,006,219 | 100% | ||
smackabandoned | 0 | 482,776,138 | 100% | ||
accepttransition | 0 | 484,138,296 | 100% | ||
tubingfeuille | 0 | 482,837,720 | 100% | ||
branchanus | 0 | 485,529,396 | 100% | ||
steemfuckeos | 0 | 429,686,861 | 7.63% | ||
picketscrub | 0 | 485,127,684 | 100% | ||
nikbutus89 | 0 | 486,351,788 | 100% | ||
alex-hm | 0 | 929,495,911 | 50% | ||
wilmer14molina | 0 | 450,661,832 | 100% | ||
eugenialobo | 0 | 378,484,836 | 100% | ||
ballesteroj | 0 | 334,525,229 | 100% | ||
jcmontilva | 0 | 387,492,714 | 100% | ||
rodriguezr | 0 | 350,231,077 | 100% | ||
marbely20 | 0 | 374,131,360 | 100% | ||
moyam | 0 | 422,432,232 | 100% | ||
emilycg | 0 | 347,269,590 | 100% | ||
darys | 0 | 388,695,456 | 100% | ||
sibaja | 0 | 392,376,376 | 100% | ||
balcej | 0 | 422,369,391 | 100% | ||
lmanjarres | 0 | 381,004,981 | 100% | ||
anaka | 0 | 420,137,415 | 100% | ||
benhurg | 0 | 422,432,130 | 100% | ||
judisa | 0 | 420,653,177 | 100% | ||
juddarivv | 0 | 422,429,024 | 100% | ||
mariamo | 0 | 361,620,242 | 100% | ||
kimmorales | 0 | 383,493,737 | 100% | ||
loraine25 | 0 | 373,504,344 | 100% | ||
kingnosa | 0 | 39,330,312 | 50% | ||
kakakk | 0 | 284,076,784 | 2.16% | ||
ascorphat | 0 | 2,349,336,519 | 2.5% | ||
priyankachauhan | 0 | 93,680,364 | 3.45% | ||
cameravisual | 0 | 2,335,556,711 | 50% | ||
amin-ove | 0 | 56,489,480 | 50% | ||
huilco | 0 | 244,544,522 | 100% | ||
hanyseek | 0 | 53,463,999 | 50% | ||
herculean | 0 | 77,769,936 | 50% | ||
combatsports | 0 | 1,280,714,063 | 4.32% | ||
jent | 0 | 1,423,674,155 | 70% | ||
donasys | 0 | 41,458,248 | 50% | ||
mtfmohammad | 0 | 81,832,029 | 25% | ||
chrisluke | 0 | 103,726,370 | 26% | ||
joannar | 0 | 70,493,025 | 25% | ||
pflanzenlilly | 0 | 167,738,295 | 50% | ||
faberleggenda | 0 | 243,607,557 | 100% | ||
mohaaking | 0 | 48,518,420 | 50% | ||
onorin | 0 | 467,096,485 | 100% | ||
lesersa | 0 | 467,031,774 | 100% | ||
celine-robichaud | 0 | 26,258,252 | 24% | ||
bergelmirsenpai | 0 | 154,660,181 | 5.5% | ||
imaloser | 0 | 85,377,006 | 50% |
Congratulations @hongtao! You have completed the following achievement on the Steem blockchain and have been rewarded with new badge(s) : <table><tr><td>https://steemitimages.com/60x70/http://steemitboard.com/@hongtao/payout.png?201903172303</td><td>You received more than 10 as payout for your posts. Your next target is to reach a total payout of 50</td></tr> </table> <sub>_You can view [your badges on your Steem Board](https://steemitboard.com/@hongtao) and compare to others on the [Steem Ranking](http://steemitboard.com/ranking/index.php?name=hongtao)_</sub> <sub>_If you no longer want to receive notifications, reply to this comment with the word_ `STOP`</sub> **Do not miss the last post from @steemitboard:** <table><tr><td><a href="https://steemit.com/drugwars/@steemitboard/drugwars-early-adopter"><img src="https://steemitimages.com/64x128/https://cdn.steemitimages.com/DQmYGN7R653u4hDFyq1hM7iuhr2bdAP1v2ApACDNtecJAZ5/image.png"></a></td><td><a href="https://steemit.com/drugwars/@steemitboard/drugwars-early-adopter">Are you a DrugWars early adopter? Benvenuto in famiglia!</a></td></tr></table> > You can upvote this notification to help all Steem users. Learn how [here](https://steemit.com/steemitboard/@steemitboard/http-i-cubeupload-com-7ciqeo-png)!
author | steemitboard |
---|---|
permlink | steemitboard-notify-hongtao-20190318t000332000z |
category | cn-stem |
json_metadata | {"image":["https://steemitboard.com/img/notify.png"]} |
created | 2019-03-18 00:03:30 |
last_update | 2019-03-18 00:03:30 |
depth | 1 |
children | 0 |
last_payout | 2019-03-25 00:03:30 |
cashout_time | 1969-12-31 23:59:59 |
total_payout_value | 0.000 HBD |
curator_payout_value | 0.000 HBD |
pending_payout_value | 0.000 HBD |
promoted | 0.000 HBD |
body_length | 1,276 |
author_reputation | 38,975,615,169,260 |
root_title | "Tensorflow入门——Keras处理分类问题,Classification with Keras" |
beneficiaries | [] |
max_accepted_payout | 1,000,000.000 HBD |
percent_hbd | 10,000 |
post_id | 81,488,940 |
net_rshares | 0 |
<div class='text-justify'> <div class='pull-left'> <br /> <center> <img width='125' src='https://i.postimg.cc/9FwhnG3w/steemstem_curie.png'> </center> <br/> </div> <br /> <br /> This post has been voted on by the **SteemSTEM** curation team and voting trail in collaboration with **@curie**. <br /> If you appreciate the work we are doing then consider [voting](https://www.steemit.com/~witnesses) both projects for witness by selecting [**stem.witness**](https://steemconnect.com/sign/account_witness_vote?approve=1&witness=stem.witness) and [**curie**](https://steemconnect.com/sign/account_witness_vote?approve=1&witness=curie)! <br /> For additional information please join us on the [**SteemSTEM discord**]( https://discord.gg/BPARaqn) and to get to know the rest of the community! </div>
author | steemstem |
---|---|
permlink | re-hongtao-tensorflow-keras-classification-with-keras-20190318t013024002z |
category | cn-stem |
json_metadata | {"app":"bloguable-bot"} |
created | 2019-03-18 01:30:27 |
last_update | 2019-03-18 01:30:27 |
depth | 1 |
children | 0 |
last_payout | 2019-03-25 01:30:27 |
cashout_time | 1969-12-31 23:59:59 |
total_payout_value | 0.000 HBD |
curator_payout_value | 0.000 HBD |
pending_payout_value | 0.000 HBD |
promoted | 0.000 HBD |
body_length | 800 |
author_reputation | 262,017,435,115,313 |
root_title | "Tensorflow入门——Keras处理分类问题,Classification with Keras" |
beneficiaries | [] |
max_accepted_payout | 1,000,000.000 HBD |
percent_hbd | 10,000 |
post_id | 81,491,993 |
net_rshares | 0 |