java深度学习之DJL创建NiN网络

1、NiN块由一个卷积层和两个1×1卷积层组成。

构建NiN块代码如下

    public static SequentialBlock niNBlock(int numChannels, Shape kernelShape,
                                           Shape strideShape, Shape paddingShape) {

        SequentialBlock tempBlock = new SequentialBlock();
        // numChannels  通道数 滤波器层数
        //kernelShape 卷积核大小
        //strideShape 步幅
        // paddingShape  填充大小
        tempBlock.add(Conv2d.builder()
                .setKernelShape(kernelShape)
                .optStride(strideShape)
                .optPadding(paddingShape)
                .setFilters(numChannels)
                .build())
                .add(Activation::relu)
                .add(Conv2d.builder()
                        .setKernelShape(new Shape(1, 1))
                        .setFilters(numChannels)
                        .build())
                .add(Activation::relu)
                .add(Conv2d.builder()
                        .setKernelShape(new