Keras入門必讀教程：手把手從安裝到解決實(shí)際問題
導(dǎo)讀：Keras是目前深度學(xué)習(xí)研究領(lǐng)域非常流行的框架。
-
允許研究人員快速搭建原型設(shè)計(jì)。 -
支持深度學(xué)習(xí)中最流行的卷積神經(jīng)網(wǎng)絡(luò)與循環(huán)神經(jīng)網(wǎng)絡(luò)，以及它們兩者的組合。 -
可以在CPU與GPU上無縫運(yùn)行。
from tensorflow import keras$ sudo pip install git+https://www.github.com/keras-team/keras-contrib.git$ pip install tensorflow-addonsfrom tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation
model = Sequential([
Dense(32, input_shape=(784,)),
Activation('relu'),
Dense(10),
Activation('softmax'),
])model = Sequential()
model.add(Dense(32,input_dim=784))
model.add(Activation('relu'))import numpy as np
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
data = np.random.random((1000,100))
labels = np.random.randint(2,size=(1000,1))
model = Sequential()
model.add(Dense(32,activation='relu', input_dim=100))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop',loss='binary_crossentropy',metrics=['accuracy'])
model.fit(data,labels,epochs=10,batch_size=32)
predictions = model.predict(data)import numpy as np
from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.layers import Conv2D, MaxPooling2D
from tensorflow.keras.optimizers import SGDx_train = np.random.random((100, 100, 100, 3))
y_train = keras.utils.to_categorical(np.random.randint(10, size=(100, 1)),
num_classes=10)
x_test = np.random.random((20, 100, 100, 3))
y_test = keras.utils.to_categorical(np.random.randint(10, size=(20, 1)),
num_classes=10)model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(100, 100, 3)))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd)
model.fit(x_train, y_train, batch_size=32, epochs=10)
score = model.evaluate(x_test, y_test, batch_size=32)from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense,Embedding,LSTM
model = Sequential()
model.add(Embedding(20000,128))
model.add(LSTM(128,dropout=0.2,recurrent_dropout=0.2))
model.add(Dense(1,activation='sigmoid'))model.compile(loss='binary_crossentropy', optimizer='adam', metrics=
['accuracy'])
model.fit(x_train, y_train, batch_size=32, epochs=15, verbose=1, validation_data=
(x_test,y_test))
score = model.evaluate(x_test, y_test, batch_size=32)model.save('./model')from tensorflow.keras.models import load_model
my_model = load_model('./model')
from __future__ import print_function
from tensorflow.keras.preprocessing import sequence
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Embedding, LSTM
from tensorflow.keras.datasets import imdb
max_features = 20000
maxlen = 80
batch_size = 32
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=max_features)
x_train = sequence.pad_sequences(x_train, maxlen=maxlen)
x_test = sequence.pad_sequences(x_test, maxlen=maxlen)model = Sequential()
model.add(Embedding(max_features, 128))
model.add(LSTM(128, dropout=0.2, recurrent_dropout=0.2))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',optimizer='adam',
metrics=['accuracy'])model.fit(x_train, y_train,
batch_size=batch_size,
epochs=15,
validation_data=(x_test, y_test))
score, acc = model.evaluate(x_test, y_test,
batch_size=batch_size)
print('Test score:', score)
print('Test accuracy:', acc)關(guān)于作者：史丹青，語憶科技聯(lián)合創(chuàng)始人兼技術(shù)負(fù)責(zé)人，畢業(yè)于同濟(jì)大學(xué)電子信息工程系。擁有多年時間的AI領(lǐng)域創(chuàng)業(yè)與實(shí)戰(zhàn)經(jīng)驗(yàn)，具備深度學(xué)習(xí)、自然語言處理以及數(shù)據(jù)可視化等相關(guān)知識與技能。是AI技術(shù)的愛好者，并擁抱一切新興科技，始終堅(jiān)信技術(shù)分享和開源精神的力量。
本文摘編自《生成對抗網(wǎng)絡(luò)入門指南》（第2版），經(jīng)出版方授權(quán)發(fā)布。
延伸閱讀《生成對抗網(wǎng)絡(luò)入門指南》（第2版）
點(diǎn)擊上圖了解及購買
轉(zhuǎn)載請聯(lián)系微信：DoctorData
推薦語：揭秘AI如何生成逼真人臉圖像，追蹤GAN前沿技術(shù)更新。
評論
圖片
表情