def compile(name,
model: Sequential,
train_samples: pd.DataFrame,
validation_samples: pd.DataFrame,
gen,
type='img'):
# model.add(Reshape((-1, num_classes), name=RESHAPED))
size = 5
steps_per_epoch = len(train_samples) // size
validation_steps = len(validation_samples) // size
train_generator = gen(train_samples, type)(size, infinite=True)
validation_generator = gen(validation_samples, type)(size, infinite=True)
adam = optimizers.Adam(lr=0.0001)
model.compile(loss='categorical_crossentropy', optimizer=adam)
history_object = model.fit_generator(train_generator,
validation_data=validation_generator,
epochs=5,
callbacks=None,
validation_steps=validation_steps,
steps_per_epoch=steps_per_epoch)
model.save_weights(name)
# model.save('fcn_model.h5')
print(history_object.history.keys())
print('Loss')
print(history_object.history['loss'])
print('Validation Loss')
print(history_object.history['val_loss'])
def get_model(idrop=0.2,
edrop=0.1,
odrop=0.25,
rdrop=0.2,
weight_decay=WEIGHT_DECAY):
model = Sequential()
model.add(
Embedding(
NB_WORDS,
128,
embeddings_regularizer=l2(weight_decay),
input_length=MAXLEN)) # , batch_input_shape=(batch_size, maxlen)))
if edrop:
model.add(Dropout(edrop))
model.add(
LSTM(128,
kernel_regularizer=l2(weight_decay),
recurrent_regularizer=l2(weight_decay),
bias_regularizer=l2(weight_decay),
dropout=idrop,
recurrent_dropout=rdrop))
if odrop:
model.add(Dropout(odrop))
model.add(
Dense(1,
kernel_regularizer=l2(weight_decay),
bias_regularizer=l2(weight_decay),
activation='sigmoid'))
optimizer = Adam(1e-3)
model.compile(loss='binary_crossentropy',
metrics=["binary_accuracy"],
optimizer=optimizer)
return model
def get_model(idrop=0.2,
edrop=0.1,
odrop=0.25,
rdrop=0.2,
weight_decay=1e-4,
lr=1e-3):
model = Sequential()
model.add(
Embedding(NB_WORDS,
128,
embeddings_regularizer=l2(weight_decay),
input_length=MAXLEN))
if edrop:
model.add(Dropout(edrop))
model.add(
LSTM(128,
kernel_regularizer=l2(weight_decay),
recurrent_regularizer=l2(weight_decay),
bias_regularizer=l2(weight_decay),
dropout=idrop,
recurrent_dropout=rdrop))
if odrop:
model.add(Dropout(odrop))
model.add(
Dense(1,
kernel_regularizer=l2(weight_decay),
bias_regularizer=l2(weight_decay)))
optimizer = Adam(lr)
model.compile(loss='mse', metrics=["mse"], optimizer=optimizer)
return model
def _build_model(self):
model = Sequential()
model.add(Dense(3, input_dim=2, activation='tanh'))
model.add(Dense(3, activation='tanh'))
model.add(Dense(self.env.action_space.n, activation='linear'))
model.compile(loss='mse', optimizer=Adam(lr=self.alpha, decay=self.alpha_decay))
return model
def main():
x_train, y_train, x_test, y_test = load_data()
model = Sequential()
model.add(
Conv2D(32,
kernel_size=(11, 11),
strides=4,
padding="same",
activation='relu',
input_shape=(48, 48, 1)))
model.add(MaxPooling2D(pool_size=(3, 3), strides=2, padding="valid"))
model.add(
Conv2D(32,
kernel_size=(5, 5),
strides=1,
padding="same",
activation='relu'))
model.add(MaxPooling2D(pool_size=(3, 3), strides=2, padding="valid"))
model.add(
Conv2D(32,
kernel_size=(3, 3),
strides=1,
padding="same",
activation='relu'))
model.add(
Conv2D(32,
kernel_size=(3, 3),
strides=1,
padding="same",
activation='relu'))
model.add(
Conv2D(32,
kernel_size=(3, 3),
strides=1,
padding="same",
activation='relu'))
model.add(Dense(1024, activation='relu'))
model.add(Dense(512, activation='relu'))
model.add(Dense(7, activation='softmax'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.fit(x_train,
y_train,
batch_size=128,
epochs=5,
verbose=1,
validation_data=(x_test, y_test))
model.save(expanduser("~/emotion/alex_net.h5"))
accuracy, fbeta = test_model(model, x_test, y_test)
print("Accuracy: %s" % accuracy)
print("F-Beta: %s" % fbeta)
def _build_model(self):
# Neural Net for Deep-Q learning Model
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=self._huber_loss,
optimizer=Adam(lr=self.learning_rate))
return model
def fit_lstm(train, batch_size, nb_epoch, neurons): X, y = train[:, 0:-1], train[:, -1] X = X.reshape(X.shape[0], 1, X.shape[1]) model = Sequential() model.add(LSTM(neurons, batch_input_shape=(batch_size, X.shape[1], X.shape[2]), stateful=True)) model.add(Dense(1)) model.compile(loss='mean_squared_error', optimizer='adam') for i in range(nb_epoch): model.fit(X, y, epochs=1, batch_size=batch_size, verbose=0, shuffle=False) model.reset_states() return model
class WindPuller(object):
def __init__(self, input_shape, lr=0.01, n_layers=2, n_hidden=8, rate_dropout=0.2, loss=risk_estimation):
print("initializing..., learing rate %s, n_layers %s, n_hidden %s, dropout rate %s." % (
lr, n_layers, n_hidden, rate_dropout))
self.model = Sequential()
self.model.add(Dropout(rate=rate_dropout, input_shape=(input_shape[0], input_shape[1])))
for i in range(0, n_layers - 1):
self.model.add(LSTM(n_hidden * 4, return_sequences=True, activation='tanh',
recurrent_activation='hard_sigmoid', kernel_initializer='glorot_uniform',
recurrent_initializer='orthogonal', bias_initializer='zeros',
dropout=rate_dropout, recurrent_dropout=rate_dropout))
self.model.add(LSTM(n_hidden, return_sequences=False, activation='tanh',
recurrent_activation='hard_sigmoid', kernel_initializer='glorot_uniform',
recurrent_initializer='orthogonal', bias_initializer='zeros',
dropout=rate_dropout, recurrent_dropout=rate_dropout))
self.model.add(Dense(1, kernel_initializer=initializers.glorot_uniform()))
# self.model.add(BatchNormalization(axis=-1, moving_mean_initializer=Constant(value=0.5),
# moving_variance_initializer=Constant(value=0.25)))
self.model.add(BatchNormalization(axis=-1))
self.model.add(Activation("relu(alpha=0., max_value=1.0)"))
opt = RMSprop(lr=lr)
self.model.compile(loss=loss,
optimizer=opt,
metrics=['accuracy'])
def fit(self, x, y, batch_size=32, nb_epoch=100, verbose=1, callbacks=None,
validation_split=0., validation_data=None, shuffle=True,
class_weight=None, sample_weight=None, initial_epoch=0):
self.model.fit(x, y, batch_size, nb_epoch, verbose, callbacks,
validation_split, validation_data, shuffle, class_weight, sample_weight,
initial_epoch)
def save(self, path):
self.model.save(path)
def load_model(self, path):
self.model = load_model(path)
return self
def evaluate(self, x, y, batch_size=32, verbose=1,
sample_weight=None, **kwargs):
return self.model.evaluate(x, y, batch_size, verbose,
sample_weight)
def predict(self, x, batch_size=32, verbose=0):
return self.model.predict(x, batch_size, verbose)
def build_network(row, col, channels, num_class):
model = Sequential()
model.add(
Conv2D(32, (8, 8), (4, 4),
activation='relu',
input_shape=(row, col, channels)))
model.add(Conv2D(64, (4, 4), (2, 2), activation='relu'))
model.add(Conv2D(64, (3, 3), (1, 1), activation='relu'))
model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dense(num_class))
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
return model
def main():
start = time.time()
# generate multiple time-series sequences
dataframe = generate_sine_data()
dataset = dataframe.values.astype('float32')
# put dataset of multiple time-series sequences
dataset = Normalize(dataset)
# create dataset
length = len(dataset)
train_size = int(length * 0.67)
test_size = length - train_size
train, test = dataset[:train_size], dataset[train_size:]
trainX, trainY = create_dataset(train)
testX, testY = create_dataset(test)
trainX = trainX[len(trainX) % BATCH_SIZE:]
trainY = trainY[len(trainY) % BATCH_SIZE:]
length_test = len(testX)
testX = testX[len(testX) % BATCH_SIZE:]
testY = testY[len(testY) % BATCH_SIZE:]
trainX = np.reshape(trainX, (trainX.shape[0], trainX.shape[1], 3))
testX = np.reshape(testX, (testX.shape[0], testX.shape[1], 3))
# construct the DNN model (LSTM + fully_connected_layer)
model = Sequential()
model.add(LSTM(HIDDEN_SIZE, batch_input_shape=(BATCH_SIZE, Tau, 3)))
model.add(Dense(3))
model.summary()
model.compile(loss='mean_squared_error',
optimizer='adam',
metrics=['accuracy'])
# learn the DNN model on training dataset
hist = model.fit(trainX,
trainY,
batch_size=BATCH_SIZE,
epochs=EPOCHS,
verbose=0,
shuffle=True)
# plot the leargning curve
if PLT:
epochs = range(1, 11)
plt.figure()
plt.plot(epochs, hist.history['loss'], label='loss/training')
plt.plot(epochs, hist.history['acc'], label='acc/training')
plt.xlabel('epoch')
plt.ylabel('acc / loss')
plt.legend()
plt.show()
plt.close()
# evaluate the DNN model on test dataset
score = model.evaluate(testX, testY, batch_size=BATCH_SIZE, verbose=0)
print('loss: {0[0]}, acc: {0[1]} on test dataset'.format(score))
# forecast Ls-steps-ahead value on the test dataset
predicted = model.predict(testX, batch_size=BATCH_SIZE)
# plot testY and predictedY
if PLT:
df_out = pd.DataFrame(predicted[:200])
df_out.columns = [
"predicted_sine", 'predicted_sine_rand', 'predicted_sine_int'
]
df_out = pd.concat([
df_out,
pd.DataFrame(
testY[:200],
columns=["input_sine", "input_sine_rand", "input_sine_int"])
])
plt.figure()
df_out.plot()
plt.show()
plt.close()
# plot the forecasting results on test dataset
if PLT:
plt.ion()
i = 0
while i < 20:
K = 3 # the number of sensor
fig = plt.figure(figsize=(8, K * 4))
plt.subplots_adjust(hspace=0.2)
for j in range(K):
plt.subplot(K, 1, j + 1)
plt.plot(range(i, i + Tau + Ls + 1),
test[length_test % BATCH_SIZE:][i:i + Tau + Ls + 1,
j],
color='silver',
label='original')
plt.plot(range(i, i + Tau),
testX[i, :, j],
color='dodgerblue',
label='input')
plt.scatter(i + Tau + Ls,
predicted[i, j],
s=15,
color='orange',
label='forecast')
plt.legend()
plt.draw()
plt.pause(1.2)
plt.clf()
i += 1
plt.close()
end = time.time()
print('elapsed_time: {}[s]'.format(end - start))
# For a single-input model with 2 classes (binary classification):
"""
from tensorflow.contrib.keras.python.keras.models import Sequential
from tensorflow.contrib.keras.python.keras.layers import Dense, Activation
# Generate dummy data
import numpy as np
data = np.random.random((1000, 100))
labels1 = 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'])
# Train the model, iterating on the data in batches of 32 samples
print("\nNo validation_set split")
model.fit(data, labels1, epochs=1, batch_size=32)
#######################################
# For a single-input model with 10 classes (categorical classification):
# Generate dummy data
import numpy as np
data = np.random.random((1000, 100))
labels2 = np.random.randint(10, size=(1000, 1))
from tensorflow.contrib.keras.python.keras.utils import to_categorical
# Convert labels to categorical one-hot encoding
one_hot_labels = to_categorical(labels2, num_classes=10)
seq.add(BatchNormalization())
seq.add(
ConvLSTM2D(filters=40,
kernel_size=(3, 3),
padding='same',
return_sequences=True))
seq.add(BatchNormalization())
seq.add(
Conv3D(filters=1,
kernel_size=(3, 3, 3),
activation='sigmoid',
padding='same',
data_format='channels_last'))
seq.compile(loss='binary_crossentropy', optimizer='adadelta')
# Artificial data generation:
#
def generate_movies(n_samples=1200, n_frames=15):
row = 80
col = 80
noisy_movies = np.zeros((n_samples, n_frames, row, col, 1), dtype=np.float)
shifted_movies = np.zeros((n_samples, n_frames, row, col, 1),
dtype=np.float)
for i in range(n_samples):
# Add 3 to 7 moving squares
n = np.random.randint(3, 8)
from tensorflow.contrib.keras.python.keras.models import Sequential
from tensorflow.contrib.keras.python.keras.layers import Dense, Dropout, Activation
from tensorflow.contrib.keras.python.keras.optimizers import SGD
from tensorflow.contrib.keras.python.keras.utils import to_categorical
import numpy as np
# Generate dummy data
x_train = np.random.random((1000, 20))
y_train = np.random.randint(2, size=(1000, 1))
x_test = np.random.random((100, 20))
y_test = np.random.randint(2, size=(100, 1))
model = Sequential()
model.add(Dense(64, input_dim=20, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', # binary classification
optimizer='rmsprop',
metrics=['accuracy'])
hist = model.fit(x_train, y_train,
validation_split=0.2,
epochs=1,
batch_size=128)
hist.history
score = model.evaluate(x_test, y_test, batch_size=128)
y_train = to_categorical(np.random.randint(10, size=(1000, 1)), num_classes=10)
x_test = np.random.random((100, 20))
y_test = to_categorical(np.random.randint(10, size=(100, 1)), num_classes=10)
model = Sequential()
# Dense(64) is a fully-connected layer with 64 hidden units.
# in the first layer, you must specify the expected input data shape:
# here, 20-dimensional vectors.
model.add(Dense(64, activation='relu', input_dim=20))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))
# specify optimizer
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True) # param adjust
model.compile(
loss='categorical_crossentropy', # multi-class
optimizer=sgd,
metrics=['accuracy'])
hist = model.fit(x_train,
y_train,
validation_split=0.2,
epochs=1,
batch_size=128)
print(hist.history)
score = model.evaluate(x_test, y_test, batch_size=128)
#create train and test lists. X-patterns, Y-intents
train_x = list(training[:, 0])
train_y = list(training[:, 1])
#print("Training data created")
#create a model Tensorflow
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 result
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.5, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd)
#fitting and saving 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")
# create model
if os.path.isfile(savefile):
model = load_model(savefile)
else:
model = Sequential()
model.add(Dense(128, input_dim=input_dimension, kernel_initializer=hidden_initializer, activation='relu'))
#model.add(Dense(128, input_dim=input_dimension, activation='relu'))
model.add(Dropout(dropout_rate))
model.add(Dense(64, kernel_initializer=hidden_initializer, activation='relu'))
model.add(Dense(2, kernel_initializer=hidden_initializer, activation='softmax'))
#model.add(Dense(64, activation='relu'))
#model.add(Dense(2, activation='softmax'))
sgd = SGD(lr=learning_rate, momentum=momentum)
model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=['acc'])
model.fit(X_train, y_train, epochs=50, batch_size=128)
predictions = model.predict_proba(X_test)
ans = pd.DataFrame(predictions,columns=['target','dmy'])
print ans
outdf = pd.concat([outdf,ans['target']],axis=1)
outdf.to_csv('./submit_keras.csv',index=False)
#save the model
#model_json = model.to_json()
#with open("./ans.json", "w") as json_file:
# json_file.write(model_json)
model = Sequential()
# if return_sequences = Flase, only last LSTM cell will slpit the output.
model.add(LSTM(32, input_shape=(look_back, data_dim), return_sequences=True))
model.add(LSTM(2))
#model.add(Dense(10))
model.add(Dropout(0.2))
model.add(Dense(1, activation='softmax'))
# try using different optimizers and different optimizer configs
model.compile('adam', 'binary_crossentropy', metrics=['accuracy'])
time_train_X, time_train_y = create_dataset(w2v_tfIdf_train_X,
train_y,
look_back=look_back)
time_test_X, time_test_y = create_dataset(w2v_tf_Idf_test_X,
test_y,
look_back=look_back)
model.fit(time_train_X,
time_train_y,
verbose=2,
epochs=10,
batch_size=100,
validation_data=[time_test_X, time_test_y])
def make_vgg16(top=True, weights='imagenet', weight_path=''):
"""
Args: top determines whether to include dense layers at the top. Weights determines
whether to use imagenet weights or pre-trained weights, in which case the filepath
must be specified via weight_path.
Creates a convolutional neural network following the VGG16 structure. There are two options:
the original structure with fully connected layers at the end, or a slimmed down model where the
FC layers are replaced by a global average pooling layer. The latter has far fewer weights.
Returns the model.
"""
model = Sequential()
model.add(ZeroPadding2D((1, 1), input_shape=(224, 224, 3)))
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)))
if weights == 'imagenet':
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'))
model.load_weights(r'D:/drivers/vgg16_weights.h5')
if top == False:
for i in range(7):
model.layers.pop()
model.outputs = [model.layers[-1].output]
model.layers[-1].outbound_nodes = []
model.add(Convolution2D(1024, (3, 3), activation='relu'))
model.add(AveragePooling2D((14, 14), padding='same'))
model.add(Flatten())
model.add(Dense(10, activation='softmax'))
else:
model.layers.pop()
model.outputs = [model.layers[-1].output]
model.layers[-1].outbound_nodes = []
model.add(Dense(10, activation='softmax'))
elif weights == 'trained':
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(10, activation='softmax'))
if top == False:
for i in range(7):
model.layers.pop()
model.outputs = [model.layers[-1].output]
model.layers[-1].outbound_nodes = []
model.add(Convolution2D(1024, (3, 3), activation='relu'))
model.add(AveragePooling2D((14, 14), padding='same'))
model.add(Flatten())
model.add(Dense(10, activation='softmax'))
model.load_weights(weight_path)
sgd = optimizers.SGD(lr=0.001, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(optimizer=sgd,
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
return model
max_features = 20000
maxlen = 100
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)
print('X_train shape:', X_train.shape)
print('X_test shape:', X_test.shape)
model = Sequential()
model.add(Embedding(max_features, 128, input_length=maxlen))
#model.add(SimpleRNN(128))
#model.add(GRU(128))
model.add(LSTM(128))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam')
model.fit(X_train, y_train, batch_size=batch_size, epochs=1,
validation_data=(X_test, y_test))
uniques, ids = np.unique(
arr, return_inverse=True) # convert 3 words into 0, 1, 2
return to_categorical(ids, len(uniques)) # convert 0, 1, 2 to one-hot
train_y_ohe = one_hot_encode_object_array(train_y)
test_y_ohe = one_hot_encode_object_array(test_y)
model = Sequential()
model.add(Dense(16, input_shape=(4, ))) # each sample has 4 features
model.add(Activation('sigmoid')) # add non-linearity to hidden layer 1
model.add(Dense(3)) # add another 3 neuron final layer
model.add(Activation('softmax')) # give it non-linearity as output
model.summary()
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=["accuracy"])
model.fit(train_X,
train_y_ohe,
validation_split=0.2,
epochs=10,
batch_size=1,
verbose=1)
loss, accuracy = model.evaluate(test_X, test_y_ohe, batch_size=32, verbose=1)
print("Accuracy = {:.2f}".format(accuracy))
def create_model():
model = Sequential()
model.add(Dense(12, input_dim=8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
w_1_2_2.append(init_weights[0][1, 1]) w_1_3_1.append(init_weights[0][0, 2]) w_1_3_2.append(init_weights[0][1, 2]) w_1_4_1.append(init_weights[0][0, 3]) w_1_4_2.append(init_weights[0][1, 3]) w_2_1.append(init_weights[2][0, 0]) w_2_2.append(init_weights[2][1, 0]) w_2_3.append(init_weights[2][2, 0]) w_2_4.append(init_weights[2][3, 0]) losses = [] accuracies = [] # use SGD optimizer with learning rate 0.1 sgd = SGD(lr=0.1) # set loss function to be mse, print out accuracy model.compile(loss='mse', optimizer=sgd, metrics=['accuracy']) # set loss function to be binary_crossentropy, print accuracy model1.compile(loss='binary_crossentropy', optimizer=sgd, metrics=['accuracy']) ####################################################### # batch_size = 1, update weights every sample; # batch_size = 100, update weights every 100 sample; # without validation_split, all dataset are trained # with validation_split=0.25, 25% dataset is saved for validation,rest for training; during training, there will be loss and val_loss, accu, and val_accu # shuffle = True, all samples of training set will be shuffled for each epoch training # epochs = 10, train with the entire dataset for 10 times # hist = fit() will record a loss for each epoch ####################################################### # hist1 = model.fit(X, y, batch_size=1, validation_split=0.25, epochs=10) # accuracy 0.75 # hist2 = model.fit(X, y, batch_size=1, epochs=1000) # accuracy 100%, loss keep dropping down to 0.0016
input_shape=(20, 20, 1),
activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
# Second convolutional layer with max pooling
model.add(Conv2D(50, (5, 5), padding="same", activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
# Hidden layer with 500 nodes
model.add(Flatten())
model.add(Dense(500, activation="relu"))
# Output layer with 32 nodes (one for each possible letter/number we predict)
model.add(Dense(32, activation="softmax"))
# Ask Keras to build the TensorFlow model behind the scenes
model.compile(loss="categorical_crossentropy",
optimizer="adam",
metrics=["accuracy"])
# Train the neural network
model.fit(X_train,
Y_train,
validation_data=(X_test, Y_test),
batch_size=32,
epochs=10,
verbose=1)
# Save the trained model to disk
model.save(MODEL_FILENAME)
test = values[n_train_hours:, :]
# split into input and outputs
train_X = train[:, :-1]
train_y = train[:, -1]
test_X = test[:, :-1]
test_y = test[:, -1]
# reshape input to be 3D [samples, timesteps, features]
train_X = train_X.reshape((train_X.shape[0], 1, train_X.shape[1]))
test_X = test_X.reshape((test_X.shape[0], 1, test_X.shape[1]))
print(train_X.shape, train_y.shape, test_X.shape, test_y.shape)
# design network
model = Sequential()
model.add(LSTM(50, input_shape=(train_X.shape[1], train_X.shape[2])))
model.add(Dense(1))
model.compile(loss='mae', optimizer='adam')
# fit network
history = model.fit(train_X,
train_y,
epochs=50,
batch_size=72,
validation_data=(test_X, test_y),
verbose=2,
shuffle=False)
# plot history
pyplot.plot(history.history['loss'], label='Training Loss')
pyplot.plot(history.history['val_loss'], label='Validation Loss')
pyplot.legend()
pyplot.show()
model.add(Embedding(input_dim=64, output_dim=256, input_length=10))
# input_dim: Size of the vocabulary
# input_length: Length of input sequences, length of each sentences
# output_dim: Dimension of the dense embedding
model.input # (?, 10),
model.output # (?, 10, 256)
model.add(LSTM(128)) # unit=128, dimensionality of the output space
model.output
model.add(Dropout(0.5)) # percent to drop out
# model.ouput # will cause error on Dropout
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
import numpy as np
x_train = np.random.random((1000, 10))
y_train = np.random.randint(2, size=(1000, 1))
x_test = np.random.random((100, 10))
y_test = np.random.randint(2, size=(100, 1))
hist=model.fit(x_train, y_train, validation_split=0.2, batch_size=16, epochs=1)
hist.history
score = model.evaluate(x_test, y_test, batch_size=16)
"""
Embedding
model.summary()
model = Sequential()
model.add(Dense(32, input_shape=(784, 10))) # return tensor (?, 784, 32)
model.add(Dense(1)) # return tensor shape (?, 784, 1)
model.summary()
import numpy as np
x = np.random.random((100, 784, 10))
y = np.random.random((100, 784, 1))
"""
## Compilation
- optimzier: 'rmsprop', 'SGD', ...
- loss: 'mse', 'categorical_crossentropy', 'binary_crossentropy', ...
- metrics: 'accuracy', ... or user_made_func
"""
# For custom metrics
from tensorflow.contrib.keras.python.keras import backend as K
def mean_pred(y_true, y_pred): # score_array = fn(y_true, y_pred) must 2 args
return K.mean(y_pred)
# For a binary classification problem
model.compile(optimizer='rmsprop', loss='mse', metrics=['accuracy', mean_pred])
hist = model.fit(x, y, validation_split=0.3, epochs=2)
print(hist.history)
dp_array.shape # compare to see for equality
(dp_array == dp_array_train).sum() # total differ
### both BatchNormalization and Droput have some basic operations prior to Normalization and Droping, Diving into the source when feeling so
#### Access middle layer output when First Dropout and then BatchNormalization
model_seq = Sequential()
model_seq.add(Dropout(0.3, input_shape=(10, )))
model_seq.add(BatchNormalization())
model_seq.add(Dense(1))
# check out weights before training
# model_seq.get_weights()
# compile and train
model_seq.compile(optimizer='SGD', loss='mse')
model_seq.fit(input_array_small, target_small, epochs=10)
model_seq.get_weights()
model_seq.save("to_delete.h5")
model_best = load_model("to_delete.h5")
###### compare two weights from two different training
# model_seq.get_weights()
###### check output
batchNorm_test = K.function(
[model_best.input, K.learning_phase()],
[model_best.layers[-2].output])([input_array_small, 0])[0]
batchNorm_train = K.function(
[model_best.input, K.learning_phase()],
print('x_train shape :', x_train.shape)
print('x_test shape :', x_test.shape)
print('y_train shape :', y_train.shape)
print('y_test shape :', y_test.shape)
batch_size = 32
epochs = 5
model = Sequential()
model.add(Dense(512, input_shape=(max_words, )))
model.add(Activation('relu'))
model.add(Dense(num_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
history = model.fit(x_train,
y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_split=0.1)
score = model.evaluate(x_test, y_test, batch_size=batch_size, verbose=1)
print('Test score:', score[0])
print('Test accuracy:', score[1])
y_train
class MLP_keras:
def __init__(self, learning_rate, layers, functions, optimizer_name,
beta=0.0, dropout=1.0):
self.n_input = layers[0]
self.n_hidden = layers[1:-1]
self.n_output = layers[-1]
self.model = Sequential()
if len(self.n_hidden) == 0:
# single layer
self.model.add(Dense(self.n_output, activation=functions[0],
kernel_regularizer=regularizers.l2(beta),
input_shape=(self.n_input,)))
elif len(self.n_hidden) == 1:
# hidden layer
self.model.add(Dense(self.n_hidden[0], activation=functions[0],
kernel_regularizer=regularizers.l2(beta),
input_shape=(self.n_input,)))
self.model.add(Dropout(dropout))
# output layer
self.model.add(Dense(self.n_output, activation=functions[1],
kernel_regularizer=regularizers.l2(beta)))
else:
# the first hidden layer
self.model.add(Dense(self.n_hidden[0], activation=functions[0],
kernel_regularizer=regularizers.l2(beta),
input_shape=(self.n_input,)))
self.model.add(Dropout(dropout))
# the second hidden layer
self.model.add(Dense(self.n_hidden[1], activation=functions[1],
kernel_regularizer=regularizers.l2(beta)))
self.model.add(Dropout(dropout))
# the output layer
self.model.add(Dense(self.n_output, activation=functions[2],
kernel_regularizer=regularizers.l2(beta)))
self.model.summary()
if optimizer_name == 'Adam': optimizer = Adam(learning_rate)
#self.model.compile(loss='mean_squared_error',
# optimizer=optimizer,
# metrics=['accuracy'])
self.model.compile(loss='categorical_crossentropy',
optimizer=optimizer,
metrics=['accuracy'])
def train(self, epochs, trn, vld=None, batch_size=32, es=0):
if vld is not None:
validation_data = (vld.x, vld.y)
if es > 0:
callbacks = [EarlyStopping(monitor='val_loss', patience=es)]
else:
callbacks = None
else:
validation_data = None
callbacks = None
self.model.fit(trn.x, trn.y,
batch_size=batch_size,
epochs=epochs,
verbose=2,
callbacks=callbacks,
validation_data=validation_data)
loss, tst_acc = self.model.evaluate(trn.x, trn.y, verbose=0)
if vld is not None:
_, vld_acc = self.model.evaluate(vld.x, vld.y, verbose=0)
else:
vld_acc = 0
return ['', loss, tst_acc, vld_acc, 0]
def evaluate(self, x_test, y_test):
score = self.model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
def score(self, tst):
return self.model.evaluate(tst.x, tst.y, verbose=0)[1]
def predict_proba(self, x):
if x is None: return None
return self.model.predict_proba(x, verbose=0)