models.py 文件源码

def convolutional(nbfilters,fsize1,fsize2,inp,pad = True,subsample = (1,1),batchnorm = True,other_activation = None):
    # fsize1 and fsize2 must be the same, and must be odd numbers
    if pad and fsize1 > 1: # double check
        inp = layers.ZeroPadding2D(padding=(int((fsize1-1)/2), int((fsize2-1)/2)))(inp)
    conv = layers.Convolution2D(nbfilters,fsize1,fsize2,border_mode = 'valid',subsample=subsample)(inp)
    if batchnorm:
        conv = layers.BatchNormalization(mode = 0,axis = 1)(conv)
    if other_activation is not None:
        conv = activation(other_activation)(conv)
    else:
        conv = activation()(conv)
    return conv