recurrent_regularizer=None, \
bias_regularizer=None, activity_regularizer=None, \
kernel_constraint=None, recurrent_constraint=None, \
bias_constraint=None, dropout=0.0, recurrent_dropout=0.0, \
implementation=1, return_sequences=False, return_state=False, \
go_backwards=False, stateful=False, unroll=False))
model.add(Dense(3, activation="softmax"))
start = time.time()
opt = optimizers.adam(lr=0.0001)
model.compile(loss="categorical_crossentropy", optimizer=opt, metrics=['accuracy'])
plot_model(model, to_file='model.png', show_shapes=True)
model.summary()
return model
if __name__ == '__main__':
X_train, y_train, X_test, y_test, train_labels, test_labels = build_inputs(False, 300)
epochs = 50 # 21
# for q in range(1, 7):
# for tt in range(1, 20):
model = build_model(X_train, 0, 0)
name = "{}-{}".format(0, 0)
early_stop = EarlyStopping(monitor='val_acc', min_delta=0.1, patience=2,
verbose=2, mode='auto')
csv_logger = CSVLogger('res/training.csv', append=True, separator=',')
history_callback = model.fit(X_train, y_train, epochs=epochs, batch_size=1000,
validation_split=0.2, callbacks=[csv_logger, early_stop])
pred = model.predict(X_test)
compute_accuracy(name, pred, test_labels, history_callback)
evalRes(pred, test_labels, y_test, name)
dense = Dense(3, kernel_constraint=max_norm(0.5))(flatten)
softmax = Activation('softmax')(dense)
model = Model(inputs=input_main, outputs=softmax)
opt = optimizers.adam(lr=0.001)
model.compile(loss="categorical_crossentropy",
optimizer=opt,
metrics=['accuracy'])
plot_model(model, to_file='model.png', show_shapes=True)
return model
N_TIME_STEPS = 330
if __name__ == '__main__':
X_train, y_train, X_test, y_test, train_labels, test_labels = build_inputs(
False, N_TIME_STEPS)
X_train = X_train.reshape(-1, X_train.shape[1], X_train.shape[2], 1)
X_test = X_test.reshape(-1, X_test.shape[1], X_test.shape[2], 1)
epochs = 50 # 21
# for q in range(1, 7):
# for tt in range(1, 20):
model = build_model(X_train, 0, 0)
name = "{}-{}".format(0, 0)
early_stop = EarlyStopping(monitor='val_acc',
min_delta=0.1,
patience=2,
verbose=2,
mode='auto')
csv_logger = CSVLogger('res/training.csv', append=True, separator=',')
history_callback = model.fit(X_train,
y_train,
