I'm experimenting (read: playing around) with LSTMs on Keras. I want to train an LSTM network so it would "track" sine waves, that is, given sine waves with different wave length, phases and lengths, it would output the rest of wave. In a sense, a many-to-many problem.
I decided that the network would need to "track" 5 sine waves simultaneously. I would generate random sine waves and use the 50 last data points as the required output of the NN.
My code is a follows:
from keras.models import Sequential
from keras.layers import LSTM, Dense, TimeDistributed,Lambda, Dropout
import numpy as np
model = Sequential()
model.add(LSTM(32, return_sequences=True, input_shape=(None, 5)))
model.add(Dropout(0.2))
model.add(LSTM(32, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(32, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(32, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(32, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(5, return_sequences=True))
model.add(Lambda(lambda x: x[:, -50:, :])) # Grab only the last 50 values
print(model.summary())
model.compile(loss='mean_squared_error',
optimizer='adam')
def make_line(length):
shift= np.random.random()
wavelength = 5+10*np.random.random()
a=np.arange(length)
answer=np.sin(a/wavelength+shift)
return answer
def make_data(seq_num,seq_len,dim):
data=np.array([]).reshape(0,seq_len,dim)
for i in range (seq_num):
mini_data=np.array([]).reshape(0,seq_len)
for j in range (dim):
line = make_line(seq_len)
line=line.reshape(1,seq_len)
mini_data=np.append(mini_data,line,axis=0)
mini_data=np.swapaxes(mini_data,1,0)
mini_data=mini_data.reshape(1,seq_len,dim)
data=np.append(data,mini_data,axis=0)
return (data)
def train_generator():
while True:
sequence_length = np.random.randint(50, 150)+50
data=make_data(1000,sequence_length,5)
x_train = data[:,:-50,:] # all but last 50
y_train = (data[:, -50:, :]) # last 50
yield x_train, y_train
model.fit_generator(train_generator(), steps_per_epoch=30, epochs=100, verbose=1,validation_data=train_generator(),validation_steps=30)
model.save('vi2h_model.h5')
I then try to generate data and use the model to predict the continuation of a sine wave:
def data_generator():
while True:
sequence_length = np.random.randint(50, 150)+50
data=make_data(1000,sequence_length,5)
x_train = data[:,:-50,:]
y_train = (data[:, -50:, :])
return x_train, y_train
x,y= data_generator()
model = load_model('vi2h_model.h5')
pred=model.predict (x)
np.save ('pred.npy',pred)
np.save ('y.npy',y)
np.save ('x.npy',x)
When inspecting the ability of the network to predict the continuation of a sine wave (comparing y[0,:,0] to pred[0,:,0] for example, in order to compare the first sine wave of the first generated datum), see that my network performed very badly:
(Edit: legend: The predicted vs actual 50 last points in a sample sine wave (blue and orange, respectively), placed after the part of the wave used as input for the NN)
What did I do wrong? And how should I my code to correctly track sine waves? Many thanks!
