def base_model():
model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same', input_shape=x_train.shape[1:]))
model.add(Activation('relu'))
model.add(Conv2D(32,(3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(64, (3,3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))
sgd = SGD(lr = 0.1, decay=1e-6, momentum=0.9 nesterov=True)
# Train model
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
return model
def build_model(self):
model = Sequential()
model.add(Dense(24, input_dim=self.state_size, activation='relu'))
model.add(Dense(24, activation='relu'))
model.add(Dense(self.action_size, activation='linear'))
model.compile(loss='mse', optimizer=Adam(lr=self.learning_rate))
return model
from keras.models import Sequential
from keras.layer import Dense
import numpy as np
x_train = np.array([1,2,3,4,5,6,7,8,9,10])
y_train = np.array([1,2,3,4,5,6,7,8,9,10])
x_test = np.array([101,102,103,104,105,106,107,108,109,110])
y_test = np.array([101,102,103,104,105,106,107,108,109,110])
model = Sequential()
model.add(Dense(5, input_dim=1, activation='relu'))
model.add(Dense(3))
model.add(Dense(1, activation='relu')
model.compile(loss='mse', optimizer='adam', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=100, batch_size=1, validation_data= (x_train, y_train))
loss, acc = model.evaluate(x_test, y_test, batch_size=1)
print("loss = ", loss)
print("acc = ", acc)
"""
Testing for easiness of making perceptron in python :)
"""
from keras.model import Sequential
from keras.layer import Dense
import numpy
numpy.random.seed(7)
dataset = numpy.loadtxt("/home/vaishnav/MLP/Wine data/train.csv",
delimiter=",")
n = input("Enter Number of Neurons\n")
X = dataset[:, :13]
Y = dataset[:, 13]
model = Sequential()
model.add(Dense(14, input_dim=13, init="uniform", activation='sigmoid'))
model.add(Dense(n, init="uniform", activation="sigmoid"))
model.add(Dense(3, init="uniform", activation="sigmoid"))
y_train = keras.utils.to_categorical(y_train, num_classes)
#building the base vgg model such that features are extracted using the vggmodel. till the end of the convulution layers
base_model=VGG16(weights='imagenet', include_top=False)
x=preprocess_input(X)#using keras's built in function
features=base_model.predict(x)
np.save(open('features.npy', 'w'),features)#saving the model obtained after passing the input through the pretrained VGG network
#building the bottleneck
x_train=np.load(open('features.npy'))#loading the trained model
top_model = Sequential()
top_model.add(Flatten())
top_model.add(Dense(4096, activation='relu'))
top_model.add(Dropout(0.9))#full layer with dropout- full6
top_model.add(Dense(4096, activation='relu'))
top_model.add(Dropout(0.8))
top_model.add(Dense(20,activation='softmax'))#full layer with dropout-full7
#compiling the model with the adadelta optimizer
top_model.compile(optimizer='Adadelta',
loss='binary_crossentropy',
metrics=['accuracy'])
#fitting data to the model as per the parameters of the paper
top_model.fit( x_train, y_train, batch_size=256, epochs=50,validation_split=0.0, validation_data=None, shuffle=True, class_weight=None, sample_weight=None, initial_epoch=0)
top_model.save('spatial_cnn.h5')#saving the weights obtained from the model
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
created by gjwei on 2017/9/28
"""
from keras.layer import Input, Dense
from keras.models import Model
inputs = Input(shape=(784, ))
x = Dense(128, activitions='relu', name='layer_1')(inputs)
x = Dense(256, activitions='relu', name='layer_2')(x)
predictions = Dense(10, activitions='softmax', name='output')(x)
model = Model(inputs=inputs, outputs=predictions)
model.compile(optimizer='rmsprop',
loss='categroy_crossentropy',
metrics=['accuracy'],
)
#!/usr/bin/env python # -*- coding: utf-8 -*- # Copyright (c) 2017 - xiongjiezk <*****@*****.**> import numpy as np from keras.layer import Input, Dense np.zeros() encoding_dim = 32 input_img = Input(shape=(784, )) encoded = Dense(encoding_dim, activation='relu')(input_img) decoded = Dense(784, activation='sigmoid')(encoded) autoencoder = Model(input=input_img, output=decoded)
#single layer neural network with Keras
import numpy as numpy
from keras.model import Sequenrial
from keras.layer import Dense, Activation
from keras.utils.visualize_util import plot
model = Sequential()
model.add(Dense(1, input_dim=500))
model.add(Activation(activation='sigmoid'))
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
data = np.random.random((1000, 500))
labels = np.random.randint(2, size=(1000, 1))
score = model.evaluate(data, labels, verbose=0)
print("Before Training: ", zip(model.metrics_names, score))
model.fit(data, labels, nb_epoch=10, batch_size=32, verbose=0)
score = model.evaluate(data, labels, verbose=0)
print("After training: ", zip(model.metrics_names, score))
plot(model, to_file='s1.png', show_shapes=True)