我如何生成两个并行conv2d

Question

k=3 # kernel size
s=2 # stride
n_filters = 32
padding = 'same'
img_ch=3 # image channels
out_ch=1 # output channel

conv2 = Conv2D(2*n_filters, (k, k),  padding=padding)(pool1)
conv2 = BatchNormalization(scale=False, axis=3)(conv2)
conv2 = Activation('relu')(conv2)    
conv2 = Conv2D(2*n_filters, (k, k),  padding=padding)(conv2)
conv2 = BatchNormalization(scale=False, axis=3)(conv2)
conv2 = Activation('relu')(conv2)    
pool2 = MaxPooling2D(pool_size=(s, s))(conv2)

我如何从conv2（keras）生成两个并行的conv2d 就像图片一样