def get_Networks(data_size, predict_size):
ReLU_net = seq.Sequential()
ReLU_net.add(linear.Linear(data_size, 100))
ReLU_net.add(r.ReLU())
ReLU_net.add(linear.Linear(100, 50))
ReLU_net.add(r.ReLU())
ReLU_net.add(linear.Linear(50, predict_size))
ReLU_net.add(softMax.SoftMax())
ELU_net = seq.Sequential()
ELU_net.add(linear.Linear(data_size, 35))
ELU_net.add(elu.ELU())
ELU_net.add(linear.Linear(35, predict_size))
ELU_net.add(softMax.SoftMax())
LeakyReLU_net = seq.Sequential()
LeakyReLU_net.add(linear.Linear(data_size, 40))
LeakyReLU_net.add(leaky.LeakyReLU())
LeakyReLU_net.add(linear.Linear(40, predict_size))
LeakyReLU_net.add(softMax.SoftMax())
SoftPlus_net = seq.Sequential()
SoftPlus_net.add(linear.Linear(data_size, 30))
SoftPlus_net.add(softPlus.SoftPlus())
SoftPlus_net.add(linear.Linear(30, predict_size))
SoftPlus_net.add(softMax.SoftMax())
return ReLU_net, ELU_net, LeakyReLU_net, SoftPlus_net
def get_Networks_with_batch(data_size, predict_size):
ReLU_net = seq.Sequential()
ReLU_net.add(linear.Linear(data_size, 100))
ReLU_net.add(batch.BatchNormalization(0.3))
ReLU_net.add(batch.ChannelwiseScaling(100))
ReLU_net.add(r.ReLU())
ReLU_net.add(linear.Linear(100, predict_size))
ReLU_net.add(softMax.SoftMax())
ELU_net = seq.Sequential()
ELU_net.add(linear.Linear(data_size, predict_size))
ELU_net.add(batch.BatchNormalization())
ELU_net.add(batch.ChannelwiseScaling(predict_size))
ELU_net.add(elu.ELU())
ELU_net.add(softMax.SoftMax())
return ReLU_net, ELU_net
def generate_vgg16():
input_shape = (224, 224, 3) # 输入: 224*244，RGB三位图
model = Sequential([
Conv2D(64, (3, 3), input_shape=input_shape, padding='same', activation='relu'),
# 卷积层，64个滤波器（卷积核），尺寸3*3，参数：输入规格，填充，激活函数
Conv2D(64, (3, 3), padding='same', activation='relu'),
# 非首层无需指定输入规格
MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
# Block 2
Conv2D(128, (3, 3), padding='same', activation='relu'),
Conv2D(128, (3, 3), padding='same', activation='relu'),
MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
# 3
Conv2D(256, (3, 3), padding='same', activation='relu'),
Conv2D(256, (3, 3), padding='same', activation='relu'),
Conv2D(256, (3, 3), padding='same', activation='relu'),
MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
# 4
Conv2D(512, (3, 3), padding='same', activation='relu'),
Conv2D(512, (3, 3), padding='same', activation='relu'),
Conv2D(512, (3, 3), padding='same', activation='relu'),
MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
# 5
Conv2D(512, (3, 3), padding='same', activation='relu'),
Conv2D(512, (3, 3), padding='same', activation='relu'),
Conv2D(512, (3, 3), padding='same', activation='relu'),
MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
# 全连接层
Flatten(),
Dense(4096, activation='relu'),
Dense(4096, activation='relu'),
Dense(1000, activation='softmax')
# 最后要做一个softmax，输出概率归一化
])
return model
from keras.layers import Dense,Embedding
from keras.layers import LSTM
from keras.datasets import imdb
# 确定一些超参数
max_features = 20000 # 使用最多的单词数
max_len = 80 # 循环截断的长度
batch_size = 32
# 加载、整理数据
(trainX,trainY),(testX,testY) = imdb.load_data(num_word = max_features)
trainX = sequence.pad_sequences(trainX,maxlen = maxlen)
testX = sequence.pad_sequences(testX,maxlen = maxlen)
# 模型构建
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')
)
# 损失函数、优化函数的配置
model.compile(loss = 'binary_crossentropy',
optimizer = 'adam',metrics=['accuracy'])
model.fit(trainX,trainY,batch_size = batch_size,epoch=15,validation_data = (testX,testY))
def VGG_16(weights_path=None):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
## ADDED THIS ##
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
## ADDED THIS ##
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
def __str__(self):
self.report2 = "After " + str(self.number_of_rounds) + " games, the winner is " + self.winner + "! The score was " + str(self.points[0]) + " - " + str(self.points[1]) + " to " + self.winner + " over " + self.loser
return self.report2
sekvens = Sequential("Sekvensielt")
rand = Random("Tilfeldig")
common = MostCommon("Mest Vanlig")
hist = Historian("Historiker", 2)
game1 = ManyGames(sekvens,rand,100) #blir ca 50/50
game1.play_many_games_with_graphics()
print(game1)
game2 = ManyGames(sekvens,hist,100) #historiker vinner klart
game2.play_many_games_with_graphics()
print(game2)
game1 = ManyGames(common,hist,100) #historiker vinner klart
exit()
def Zipper(A, B):
C = [[A[i], B[i]] for i in range(len(A))]
return C
def Unzipper(C):
A = [C[i][0] for i in range(len(C))]
B = [C[i][1] for i in range(len(C))]
return A, B
C = Zipper(A, B)
if kind == 'r':
shuffle(C)
A, B = Unzipper(C)
T = Sequential.Memorize(num, A, B)
if er == 'y':
T.StartM(ki)
elif er == 'n':
T.StartN(ki)
elif kind == 's':
A, B = Unzipper(C)
T = Sequential.Memorize(num, A, B)
if er == 'y':
T.StartM(ki)
elif er == 'n':
T.StartN(ki)
a=np.sort(a)
for i in range(Y.shape[0]):
for j in range(a.shape[0]):
if Y[i]==a[j]:
Y[i]=j
# convert class labels to on-hot encoding
Y = np_utils.to_categorical(Y,num_classes) #Y.shape Y[48]
#suffle dataset
x,y = shuffle(X,Y, random_state=2)
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=2)
# Defining the model
input_shape=X[0].shape #img_data.shape
print(input_shape)
model = Sequential()
model.add(Conv2D(96,(11,11),subsample=(4, 4),input_shape=input_shape))#model.output_shape
model.add(MaxPooling2D(pool_size=(2, 2)))#model.output_shape
model.add(ZeroPadding2D(padding=(2, 2)))#model.output_shape
model.add(Conv2D(256, (5, 5)))#model.output_shape
model.add(MaxPooling2D(pool_size=(2, 2)))#model.output_shape
model.add(ZeroPadding2D(padding=(1, 1)))#model.output_shape
model.add(Conv2D(384, (3,3)))#model.output_shape
model.add(ZeroPadding2D(padding=(1, 1)))
model.add(Conv2D(384, (3,3)))#model.output_shape
model.add(ZeroPadding2D(padding=(1, 1)))#model.output_shape
model.add(Conv2D(256, (3,3)))#model.output_shape
model.add(MaxPooling2D(pool_size=(2, 2)))#model.output_shape
model.add(Flatten())#model.output_shape
model.add(Dense(2048))#model.output_shape
model.add(Dense(2048,name="dense_layer"))#model.output_shape
elif self.action1 < self.action2:
self.points = [0, 1]
self.winner = str(self.player2) + ' is the winner'
self.player1.recieve_results(self.player2, self.action2)
self.player2.recieve_results(self.player1, self.action1)
def __str__(self):
self.report = str(self.player1) + ": " + str(
self.action1) + "\n" + str(self.player2) + ": " + str(
self.action2) + "\n" + str(self.winner) + "\n"
return self.report
a = Random("Frida")
b = Sequential("Simone")
spill = SingleGame(a, b)
spill.play_game()
print(spill)
d = Random("Frida")
b = Sequential("Simone")
spill = SingleGame(a, b)
spill.play_game()
print(spill)
c = Random("Frida")
b = Sequential("Simone")
def build_classifier():
classifier=Sequential()
classifier.add(Convolution2D(32,3,3,input_shape=(128,128,3),activation='relu'))
classifier.add(MaxPooling2D(pool_size=(2,2),strides=(2,2),padding='same'))
classifier.add(Convolution2D(64,3,3,activation='relu'))
classifier.add(MaxPooling2D(pool_size=(2,2),strides=(2,2),padding='same'))
classifier.add(Flatten())
classifier.add(Dense(output_dim=64,activation='relu'))
classifier.add(Dropout(p=0.5))
classifier.add(Dense(output_dim=1,activation='sigmoid'))
classifier.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
return classifier
from f keras.models import Sequential from keras.layers import Dense model = Sequential([Dense(2, input_dim=1), Dense(1)]) # from keras.models import Sequential # from keras.layers import Dense # from keras.utils import plot_model # model = Sequential() # model.add(Dense(2, input_dim=1)) # model.add(Dense(1)) # summarize layers print(model.summary()) # plot graph plot_model(model, to_file='multilayer_perceptron_graph.png')
num = raw_input('>')
num = int(num)
A = locals()['A' + str(num - 1)]
B = locals()['B' + str(num - 1)]
def Zipper(A, B):
C = [[A[i], B[i]] for i in range(len(A))]
return C
def Unzipper(C):
for i in range(len(C)):
A[i] = C[i][0]
B[i] = C[i][1]
return A, B
if kind == 's':
T = Sequential.Test(num, A, B)
T.Start()
elif kind == 'r':
C = Zipper(A, B)
shuffle(C)
A, B = Unzipper(C)
T = Sequential.Test(num, A, B)
T.Start()
else:
print "Please input correct text."
exit()
rom keras.models import Sequential from keras.layers import Convolution2D from keras.layers import MaxPooling2D from keras.layers import Flatten from keras.layers import Dense # Initialising the CNN classifier = Sequential() # Step 1 - Convolution classifier.add(Convolution2D(32, 3, 3, input_shape = (64, 64, 3), activation = 'relu')) # Step 2 - Pooling classifier.add(MaxPooling2D(pool_size = (2, 2))) # Adding a second convolutional layer classifier.add(Convolution2D(32, 3, 3, activation = 'relu')) classifier.add(MaxPooling2D(pool_size = (2, 2))) # Step 3 - Flattening classifier.add(Flatten()) # Step 4 - Full connection classifier.add(Dense(output_dim = 128, activation = 'relu')) classifier.add(Dense(output_dim = 1, activation = 'sigmoid')) # Compiling the CNN classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy']) # Part 2 - Fitting the CNN to the images
import keras.models import Sequential from keras.layers import Dense model = Sequential() (hand,field,action,next_field)
# create train and test lists. X - patterns, Y - intents
train_x = list(training[:,0])
train_y = list(training[:,1])
print("Training data created")
"""# 4. Build machine learning model
After creating training data, build a deep neaural network that has 3 layers. The following code uses Keras' sequential API.
The model is trained for 200 epochs, achieving 100% accuracy on the model.
"""
# Create model - 3 layers. First layer 128 neurons, second layer 64 neurons and 3rd output layer contains number of neurons
# equal to number of intents to predict output intent with softmax
model = Sequential()
model.add(Dense(128, input_shape=(len(train_x[0]),), activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(len(train_y[0]), activation='softmax'))
# Compile model. Stochastic gradient descent with Nesterov accelerated gradient gives good results for this model
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
#fitting and saving the model
hist = model.fit(np.array(train_x), np.array(train_y), epochs=200, batch_size=5, verbose=1)
model.save('chatbot_model.h5', hist)
print("model created")
import keras import keras.models import Sequential import keras.layers Dense, Dropout, Flatten from keras.layers import Conv2D, MaxPooling2D from keras.callbacks import TensorBoard import os import numpy as np import random model = Sequential() model.add(Conv2D(32, (3, 3), padding = 'same', input_shape(176, 200, 3), activation = 'relu')) model.add(Conv2D(32, (3, 3), activation = 'relu')) model.add(MaxPooling2D(pool_size = (2, 2))) model.add(Dropout(0.2)) model.add(Conv2D(64, (3, 3), padding = 'same', activation = 'relu')) model.add(Conv2D(64, (3, 3), activation = 'relu')) model.add(MaxPooling2D(pool_size = (2, 2))) model.add(Dropout(0.2)) model.add(Conv2D(128, (3, 3), padding = 'same', activation = 'relu')) model.add(Conv2D(128, (3, 3), activation = 'relu')) model.add(MaxPooling2D(pool_size = (2, 2))) model.add(Dropout(0.2)) # fully-connected dense layer model.add(Flatten()) model.add(Dense(512, activation = 'relu'))