训练损失是 Nan - 但训练数据都在范围内,没有 null

training loss is Nan - but trainning data is all in range without null

当我执行 model.fit(x_train_lstm, y_train_lstm, epochs=3, shuffle=False, verbose=2)

作为nan,我总是吃亏:

Epoch 1/3
73/73 - 5s - loss: nan - accuracy: 0.5417 - 5s/epoch - 73ms/step
Epoch 2/3
73/73 - 5s - loss: nan - accuracy: 0.5417 - 5s/epoch - 74ms/step
Epoch 3/3
73/73 - 5s - loss: nan - accuracy: 0.5417 - 5s/epoch - 73ms/step

我的x_training字形为(2475, 48),y_train字形为(2475,)

全部在 (-1,1) 范围内:

我的模型是这样的:

Model: "sequential_2"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 lstm_6 (LSTM)               (None, 160, 128)          90624     
                                                                 
 dropout_4 (Dropout)         (None, 160, 128)          0         
                                                                 
 lstm_7 (LSTM)               (None, 160, 64)           49408     
                                                                 
 dropout_5 (Dropout)         (None, 160, 64)           0         
                                                                 
 lstm_8 (LSTM)               (None, 32)                12416     
                                                                 
 dense_2 (Dense)             (None, 1)                 33        
                                                                 
=================================================================
Total params: 152,481
Trainable params: 152,481
Non-trainable params: 0

现在不知道哪里可以尝试更多~

我的型号代码是:

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, LSTM
from tensorflow.keras.layers import Dropout

def create_model(win = 100, features = 9):
    model = Sequential()
    model.add(LSTM(units=128, activation='relu', input_shape=(win, features),
        return_sequences=True))
    model.add(Dropout(0.1))
    model.add(LSTM(units=64, activation='relu', return_sequences=True))
    model.add(Dropout(0.2))

    # no need return sequences from 'the last layer'
    model.add(LSTM(units=32))

    # adding the output layer
    model.add(Dense(units=1, activation='sigmoid'))

    # may also try mean_squared_error
    model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
    return model

这里我绘制了一些 train_y 样本:

两件事:尝试标准化您的时间序列数据并使用 relu 作为 lstm 层的激活函数不是 'conventional'。检查此 post 以获得更多见解。一个例子:

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, LSTM
from tensorflow.keras.layers import Dropout
import tensorflow as tf

layer = tf.keras.layers.Normalization(axis=-1)
x = tf.random.normal((500, 100, 9))
y = tf.random.uniform((500, ), dtype=tf.int32, maxval=2)
layer.adapt(x)

def create_model(win = 100, features = 9):
    model = Sequential()
    model.add(layer)
    model.add(LSTM(units=128, activation='tanh', input_shape=(win, features),
        return_sequences=True))
    model.add(Dropout(0.1))
    model.add(LSTM(units=64, activation='tanh', return_sequences=True))
    model.add(Dropout(0.2))

    model.add(LSTM(units=32))

    model.add(Dense(units=1, activation='sigmoid'))

    model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
    return model

model = create_model()

model.fit(x, y, epochs=20)

2022.Mar.17更新

经过进一步的调试,我最终发现问题其实是因为我新添加的特征包含np.inf,删除那些行后,我的问题解决了,我现在可以看到损失值[=16] =]

6/6 [==============================] - 2s 50ms/step - loss: 0.6936 - accuracy: 0.5176

注意,np.inf 有符号,所以确保 np.inf-np.inf 都被删除:

all_dataset = all_dataset[all_dataset.feature_issue != np.inf]
all_dataset = all_dataset[all_dataset.feature_issue != -np.inf]

2022.Mar.16

经过一些调试,我解决了 2 个新添加的功能实际上导致了问题。所以,问题来自数据,但与其他人不同的是,我的数据不包含nan,没有超出范围(本来我认为所有数据都需要归一化)

但我还不能说出原因,因为它们看起来不错

明天我会继续研究它,欢迎任何建议!