image= fluid.layers.data(name = 'image',shape = [1,1,-1,-1], dtype='float32')
y_act = fluid.layers.data(name='y_act', shape=[1,1,-1,-1], dtype='float32')
y_pre = self.conv2d_neural_network(image)

为什么调用模型会提示错误如下：

Due to the settings of padding(0), filter_size(2) and stride(2), the output size is less than 0, please check again. Input_size:-1 at