GRU 层参数个数和理论值不相符

在建立RNN模型时，发现GRU层的参数个数和理论值不相符。

按照公式计算，GRU层的参数应该是 (32✖(32+1)+32✖32)✖3=6240，但是我的模型运行出来是6336，这是为什么呢？

求指点~~

from keras.models import Sequential
from keras import layers
from keras.optimizers import RMSprop

model = Sequential()

model.add(layers.Conv1D(32,5,activation ='relu',
         input_shape=(None,float_data.shape[-1])))
model.add(layers.MaxPooling1D(3))
model.add(layers.Conv1D(32,5,activation='relu'))
model.add(layers.GRU(32,dropout=0.1,recurrent_dropout=0.5))
model.add(layers.Dense(1))

model.summary()

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv1d (Conv1D)              (None, None, 32)          2272      
_________________________________________________________________
max_pooling1d (MaxPooling1D) (None, None, 32)          0         
_________________________________________________________________
conv1d_1 (Conv1D)            (None, None, 32)          5152      
_________________________________________________________________
gru (GRU)                    (None, 32)                6336      
_________________________________________________________________
dense (Dense)                (None, 1)                 33        
=================================================================
Total params: 13,793
Trainable params: 13,793
Non-trainable params: 0
_________________________________________________________________

正确的计算方法是3*(32*(32+32+1)+32)=6336，你可能是忘了算偏置项