def free_attn_lstm(dataset_object: LSTM_data):
X_train, X_test, Y_train, Y_test = dataset_object.get_memory()
X_train, X_test = X_train[:, :, :-12], X_test[:, :, :-12]
regressor = Sequential()
# Adding the first LSTM layer and some Dropout regularisation
regressor.add(LSTM(units=NEURONS,
return_sequences=True,
activation=ACTIVATION,
recurrent_activation="sigmoid",
input_shape=(X_train.shape[1], X_train.shape[2]),
bias_regularizer=regularizers.l2(BIAIS_REG),
activity_regularizer=regularizers.l2(L2)
))
regressor.add(Dropout(DROPOUT))
regressor.add(LSTM(units=NEURONS,
activation=ACTIVATION,
recurrent_activation="sigmoid",
return_sequences=True,
bias_regularizer=regularizers.l2(BIAIS_REG),
activity_regularizer=regularizers.l2(L2)
))
regressor.add(Dropout(DROPOUT))
# Adding a second LSTM layer and some Dropout regularisation
regressor.add(LSTM(units=NEURONS,
activation=ACTIVATION,
recurrent_activation="sigmoid",
bias_regularizer=regularizers.l2(BIAIS_REG),
activity_regularizer=regularizers.l2(L2)
))
regressor.add(Dropout(DROPOUT))
# Adding the output layer
regressor.add(Dense(units=1,
activation='relu',
bias_regularizer=regularizers.l2(BIAIS_REG),
activity_regularizer=regularizers.l2(L2)
)
)
optim = Adam()
# Compiling the RNN
regressor.compile(optimizer=optim, loss='mean_squared_error')
# Fitting the RNN to the Training set
history= regressor.fit(X_train,
Y_train,
epochs=EPOCHS,
batch_size=BATCH_SIZE,
validation_data=(X_test, Y_test),
callbacks=[REDUCE_LR, EARLY_STOP]
)
regressor.save("data/weights/free_attn_lstm_no_senti")
plot_train_loss(history)
evaluate(regressor,X_test,Y_test, dataset_object,name="free_attn_lstm", senti="no")
def Train(self, input, target):
X_train, X_test, Y_train, Y_test = train_test_split(input, target, train_size=0.75)
Y_train = np.asarray(Y_train)
Y_test = np.array(Y_test)
X_train = np.reshape(X_train, [-1, X_train[0].shape[0], X_train[0].shape[1]])
X_test = np.reshape(X_test, [-1, X_train[0].shape[0], X_train[0].shape[1]])
model = Sequential()
model.add(Conv1D(16, 3, padding='same', input_shape=input[0].shape))
model.add(LeakyReLU(alpha=0.2))
model.add(BatchNormalization())
model.add(GRU(16, return_sequences=True))
# model.add(Activation("sigmoid"))
# model.add(LSTM(lstm_out))
model.add(Flatten())
model.add(Dense(8, activity_regularizer=l2(0.001)))
# model.add(GRU(lstm_out, return_sequences=True))
# model.add(LSTM(lstm_out))
# model.add(Dense(20, activity_regularizer=l2(0.001)))
model.add(Activation("relu"))
model.add(Dense(2))
model.compile(loss=mean_absolute_error, optimizer='nadam',
metrics=[RootMeanSquaredError(), MAE])
print(model.summary())
batch_size = 12
epochs = 100
reduce_lr_acc = ReduceLROnPlateau(monitor='val_loss', factor=0.9, patience=epochs / 10, verbose=1, min_delta=1e-4, mode='max')
model.fit(X_train, Y_train,
epochs=epochs,
batch_size=batch_size, validation_data=(X_test, Y_test), callbacks=[reduce_lr_acc])
model.save("PositionEstimation.h5", overwrite=True)
# acc = model.evaluate(X_test,
# Y_test,
# batch_size=batch_size,
# verbose=0)
predicted = model.predict(X_test, batch_size=batch_size)
# predicted = out.ravel()
res = pd.DataFrame({"predicted_x": predicted[:, 0],
"predicted_y": predicted[:, 1],
"original_x": Y_test[:, 0],
"original_y": Y_test[:, 1]})
res.to_excel("res.xlsx")
def dense_net(dataset_object:LSTM_data):
X_train, X_test, Y_train, Y_test = dataset_object.get_memory()
print(X_test.shape, X_train.shape)
X_train = X_train.reshape(X_train.shape[0],X_train.shape[2])
X_test=X_test.reshape(X_test.shape[0], X_test.shape[2])
X_train, X_test = X_train[:, :-12], X_test[:, :-12]
print(X_test.shape, X_train.shape)
regressor = Sequential()
regressor.add(Dense(units=EPOCHS,
activation='relu',
bias_regularizer=regularizers.l2(BIAIS_REG),
activity_regularizer=regularizers.l2(L2)
))
regressor.add(Dense(units=EPOCHS,
activation='relu',
bias_regularizer=regularizers.l2(BIAIS_REG),
activity_regularizer=regularizers.l2(L2)
))
regressor.add(Dense(units=EPOCHS,
activation='relu',
bias_regularizer=regularizers.l2(BIAIS_REG),
activity_regularizer=regularizers.l2(L2)
))
regressor.add(Dropout(DROPOUT))
regressor.add(Dense(units=1,
activation='relu',
bias_regularizer=regularizers.l2(BIAIS_REG),
activity_regularizer=regularizers.l2(L2)
))
optim = Adam()
# Compiling the RNN
regressor.compile(optimizer=optim, loss='mean_squared_error')
# Fitting the RNN to the Training set
history= regressor.fit(X_train,
Y_train,
epochs=EPOCHS,
batch_size=BATCH_SIZE,
validation_data=(X_test, Y_test),
callbacks=[EARLY_STOP, REDUCE_LR])
regressor.save("data/weights/dense_no_senti")
plot_train_loss(history)
evaluate(regressor, X_test,Y_test, dataset_object,name="dense", senti="yes")