keras 提取最佳值损失

Question

网络就像

inp=Input((1,12))

dense0=GRU(200,activation='relu',recurrent_dropout=0.2,return_sequences=True)(inp)

drop0=Dropout(0.3)(dense1)

dense1=GRU(200,activation='relu',recurrent_dropout=0.2)(drop0)

drop1=Dropout(0.3)(dense1)

dense1=Dense(200,activation='relu')(inp)

drop1=Dropout(0.3)(dense1)

dense2=Dense(200,activation='relu')(drop1)

drop2=Dropout(0.3)(dense2)

dense3=Dense(100,activation='relu')(drop2)

drop3=Dropout(0.3)(dense3)

out=Dense(6,activation='relu')(drop2)

md=Model(inputs=inp,outputs=out)

##md.summary()

opt=keras.optimizers.rmsprop(lr=0.000005)

md.compile(opt,loss='mean_squared_error')

esp=EarlyStopping(patience=90, verbose=1, mode='auto')

md.fit(x_train.reshape((8105,1,12)),y_train.reshape((8105,1,6)),batch_size=2048,epochs=1500,callbacks=[esp], validation_split=0.2)

输出：

    Epoch 549/1500

    6484/6484 [==============================] - 0s 13us/step - loss: 0.0589 - val_loss: 0.0100

    Epoch 550/1500

    6484/6484 [==============================] - 0s 10us/step - loss: 0.0587 - val_loss: 0.0099

    Epoch 551/1500

    6484/6484 [==============================] - 0s 12us/step - loss: 0.0584 - val_loss: 0.0100

    Epoch 552/1500

    6484/6484 [==============================] - 0s 12us/step - loss: 0.0593 - val_loss: 0.0100

    Epoch 553/1500

    6484/6484 [==============================] - 0s 12us/step - loss: 0.0584 - val_loss: 0.0100

    Epoch 554/1500

    6484/6484 [==============================] - 0s 15us/step - loss: 0.0587 - val_loss: 0.0101

    Epoch 555/1500

    6484/6484 [==============================] - 0s 12us/step - loss: 0.0583 - val_loss: 0.0100

    Epoch 556/1500

    6484/6484 [==============================] - 0s 13us/step - loss: 0.0578 - val_loss: 0.0101