Question

我的X_train形状为（171,10,1），y_train形状为（171，）（包含1到19的值）。输出应该是19个类别中每个类别的概率。我正在尝试使用RNN对19个类进行分类。

from sklearn.preprocessing import LabelEncoder,OneHotEncoder
label_encoder_X=LabelEncoder()
label_encoder_y=LabelEncoder()

y_train=label_encoder_y.fit_transform(y_train)
y_train=np.array(y_train)

X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))


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


regressor = Sequential()

regressor.add(LSTM(units = 100, return_sequences = True, input_shape=( 
(X_train.shape[1], 1)))
regressor.add(Dropout(rate=0.15))

regressor.add(LSTM(units = 100, return_sequences =False))#False caused the 
exception ndim
regressor.add(Dropout(rate=0.15))


regressor.add(Flatten())
regressor.add(Dense(units= 19,activation='sigmoid'))
regressor.compile(optimizer = 'rmsprop', loss = 'mean_squared_error')

regressor.fit(X_train, y_train, epochs = 250, batch_size = 16)

Answer 1

在第二个LSTM层中设置return_sequences =False时，结果是（None，100）不再需要Flatten()。您可以根据需要在第二个LSTM层中设置return_sequences=True或删除regressor.add(Flatten())。

此外，如果要获取19个类别中每个类别的概率，则标签数据应为一格形式。使用keras.utils.to_categorical：

one_hot_labels = keras.utils.to_categorical(y_train, num_classes=19) #(None,19)
regressor.fit(X_train, one_hot_labels, epochs = 250, batch_size = 16)

输入0与lstm_93层不兼容：预期ndim = 3，找到的ndim = 2

1 个答案: