我看到LSTM模型的纪元图中的跳跃跳跃。 (附有SCREENSHOT)它告诉我什么? (过度拟合?,错误的功能,错误的激活不必要的层?等等。)
# Model
time_input= Input(shape=(timesteps,data_dim)) #inputs dimension
DKLOC_input= Input(shape=(timesteps,data_dim))
LSTM_outs=LSTM(hidden_dim, unroll= True, return_sequences=True)(time_input)
MLP_inputs=concatenate([LSTM_outs,Feature_Data_input])
MLP_outs= Dense(MLP_hidden_dim, activation='relu')(MLP_inputs)
MLP_outs= Dense(MLP_hidden_dim, activation='relu')(MLP_outs)
outs= Dense(data_dim, activation="linear")(MLP_outs)
#optimizaiton # compile #fit
model = Model(inputs=[time_input,Feature_Data_input], outputs=[outs])
model.compile(loss='mse', optimizer="adam", metrics=['mse', 'mae', 'mape', 'cosine'])
history = model.fit(x=[input_data, Feature_Data_train] , y= truth, batch_size=1, epochs=1000, verbose=2)
Epoch 999/1000 - 0s - 损失:0.0132 - mean_squared_error:0.0132 - mean_absolute_error:0.0619 - mean_absolute_percentage_error:45287253.3333 - cosine_proximity:-6.5984e-01 Epoch 1000/1000 - 0s - 损失:0.0132 - mean_squared_error:0.0132 - mean_absolute_error:0.0618 - mean_absolute_percentage_error :45145968.0000 - cosine_proximity:-6.5985e-01
我将首先使用大于1的batch_size。您希望优化器考虑多个数据点,而不是当时的单个样本。希望您的数据样本不同,因此您希望优化考虑一组平均值。