Conv1d(in_channels,out_channels,kernel_size,stride=1,padding=0,dilation=1,groups=1,bias=True)
model.add(Conv1D(filters=nn_params["input_filters"], kernel_size=nn_params["filter_length"], strides=1, padding='valid', activation=nn_params["activation"], kernel_regularizer=l2(nn_params["reg"])))
例:输入维度为(None,1000,4)
第一维度:None
第二维度:output_length = int((input_length - nn_params["filter_length"] + 1))
在此情况下为:output_length = (1000 + 2*padding - filters +1)/ strides = (1000 + 2*0 -32 +1)/1 = 969
第三维度:filters
本文链接:http://task.lmcjl.com/news/12155.html