我創建了一個帶有 LSTM 層的模型，如下所示，并希望在訓練步驟之后獲取內部狀態（隱藏狀態和單元狀態）并保存它。在訓練步驟之后，我將使用網路進行預測，并希望在下一個訓練步驟之前使用保存的內部狀態重新初始化 LSTM。這樣我就可以在每個訓練步驟之后從同一點繼續。我還沒有找到對當前版本的 tensoflow 有幫助的東西，即 2.x。
import tensorflow as tf
class LTSMNetwork(object):
def __init__(self, num_channels, num_hidden_neurons, learning_rate, time_steps, batch_size):
self.num_channels = num_channels
self.num_hidden_neurons = num_hidden_neurons
self.learning_rate = learning_rate
self.time_steps = time_steps
self.batch_size =batch_size
def lstm_model(self):
self.model = tf.keras.Sequential()
self.model.add(tf.keras.layers.LSTM(batch_input_shape=(self.batch_size, self.time_steps, self.num_channels),
units=self.num_hidden_neurons[0],
activation='tanh', recurrent_activation='sigmoid',
return_sequences=True, stateful=True))
#self.model.add(tf.keras.layers.LSTM(units=self.num_hidden_neurons[1], stateful=True))
hidden_layer = tf.keras.layers.Dense(units=self.num_hidden_neurons[1], activation=tf.nn.sigmoid)
self.model.add(hidden_layer)
self.model.add(tf.keras.layers.Dense(units=self.num_channels, name="output_layer", activation=tf.nn.tanh))
self.model.compile(optimizer=tf.optimizers.Adam(learning_rate=self.learning_rate),
loss='mse', metrics=['binary_accuracy'])
return self.model
if __name__=='__main__':
num_channels = 3
num_hidden_neurons = [150, 100]
learning_rate = 0.001
time_steps = 1
batch_size = 1
lstm_network = LTSMNetwork(num_channels=num_channels, num_hidden_neurons=num_hidden_neurons,
learning_rate=learning_rate, time_steps=time_steps, batch_size=batch_size)
model = lstm_network.lstm_model()
model.summary()
uj5u.com熱心網友回復：
例如，您可以定義自定義Callback并在每個時期保存隱藏狀態和單元狀態。之后，您可以選擇要從哪個 epoch 中提取狀態，然后lstm_layer.reset_states(*)再次用于設定初始狀態：
import tensorflow as tf
class LTSMNetwork(object):
def __init__(self, num_channels, num_hidden_neurons, learning_rate, time_steps, batch_size):
self.num_channels = num_channels
self.num_hidden_neurons = num_hidden_neurons
self.learning_rate = learning_rate
self.time_steps = time_steps
self.batch_size =batch_size
def lstm_model(self):
self.model = tf.keras.Sequential()
self.model.add(tf.keras.layers.LSTM(batch_input_shape=(self.batch_size, self.time_steps, self.num_channels),
units=self.num_hidden_neurons[0],
activation='tanh', recurrent_activation='sigmoid',
return_sequences=True, stateful=True))
hidden_layer = tf.keras.layers.Dense(units=self.num_hidden_neurons[1], activation=tf.nn.sigmoid)
self.model.add(hidden_layer)
self.model.add(tf.keras.layers.Dense(units=self.num_channels, name="output_layer", activation=tf.nn.tanh))
self.model.compile(optimizer=tf.optimizers.Adam(learning_rate=self.learning_rate),
loss='mse', metrics=['binary_accuracy'])
return self.model
states = {}
class CustomCallback(tf.keras.callbacks.Callback):
def __init__(self, lstm_layer):
self.lstm_layer = lstm_layer
def on_epoch_end(self, epoch, logs=None):
states[epoch] = lstm_layer.states
num_channels = 3
num_hidden_neurons = [150, 100]
learning_rate = 0.001
time_steps = 1
batch_size = 1
lstm_network = LTSMNetwork(num_channels=num_channels, num_hidden_neurons=num_hidden_neurons,
learning_rate=learning_rate, time_steps=time_steps, batch_size=batch_size)
model = lstm_network.lstm_model()
lstm_layer = model.layers[0]
x = tf.random.normal((1, 1, 3))
y = tf.random.normal((1, 1, 3))
model.fit(x, y, epochs=5, callbacks=[CustomCallback(lstm_layer)])
model.summary()
lstm_layer.reset_states(states[0]) # Sets hidden state from first epoch.
States由 5 個 epoch 中的每一個的 5 個內部狀態組成。
轉載請註明出處，本文鏈接：https://www.uj5u.com/qiye/429746.html