进入Demo所在目录

cd /E/MAX78000/MAXSDK/Examples/MAX78000/CNN/kws20_demo

执行编译

make

如果之前已经被编译过了，可以先清除，再make

make distclean

选择板型

根据自己用的开发板不一样，注释掉BOARD=EvKit_V1

To compile code for MAX78000 EVKIT enable BOARD=EvKit_V1 in project.mk:

# Specify the board used
ifeq "$(BOARD)" ""
BOARD=EvKit_V1
#BOARD=FTHR_RevA
endif
To compile code for MAX78000 Feather board enable BOARD=FTHR_RevA in project.mk:

# Specify the board used
ifeq "$(BOARD)" ""
#BOARD=EvKit_V1
BOARD=FTHR_RevA
endif

如果你用的IDE来开发的，可以这里设置。

之后可以打开这个文件，来看一下

开始烧录

如果你是Window上整的

openocd -s $MAXIM_PATH/Tools/OpenOCD/scripts -f interface/cmsis-dap.cfg -f target/max78000.cfg -c "program build/MAX78000.elf reset exit"

然后就烧录进去了，没了，里面本来的那个Demo没了，变成这玩意了

如果你在Linux上

./openocd -f tcl/interface/cmsis-dap.cfg -f tcl/target/max78000.cfg -c "program build/MAX78000.elf verify reset exit"

我看代码其实不应该是这样的，但暂时没找出来问题出在了哪里。

时隔一周回头再来

修改makefile

修改project.mk

修改配置

成功

原理部分

这个Demo的软件框图如下

CNN Model 卷积神经网络模型

The KWS20 v.3 Convolutional Neural Network (CNN) model consists of 1D CNN with 8 layers and one fully connected layer to recognize keyword from 20 words dictionary used for training.

class AI85KWS20Netv3(nn.Module):
    """
    Compound KWS20 v3 Audio net, all with Conv1Ds
    """

    # num_classes = n keywords + 1 unknown
    def __init__(
            self,
            num_classes=21,
            num_channels=128,
            dimensions=(128, 1),  # pylint: disable=unused-argument
            bias=False,
            **kwargs

    ):
        super().__init__()
        self.drop = nn.Dropout(p=0.2)
        # Time: 128 Feature :128
        self.voice_conv1 = ai8x.FusedConv1dReLU(num_channels, 100, 1, 
                                                stride=1, padding=0,
                                                bias=bias, **kwargs)
        # T: 128 F: 100
        self.voice_conv2 = ai8x.FusedConv1dReLU(100, 96, 3, 
                                                stride=1, padding=0,
                                                bias=bias, **kwargs)
        # T: 126 F : 96
        self.voice_conv3 = ai8x.FusedMaxPoolConv1dReLU(96, 64, 3, 
                                                       stride=1, padding=1,
                                                       bias=bias, **kwargs)
        # T: 62 F : 64
        self.voice_conv4 = ai8x.FusedConv1dReLU(64, 48, 3, 
                                                stride=1, padding=0,
                                                bias=bias, **kwargs)
        # T : 60 F : 48
        self.kws_conv1 = ai8x.FusedMaxPoolConv1dReLU(48, 64, 3, 
                                                     stride=1, padding=1,
                                                     bias=bias, **kwargs)
        # T: 30 F : 64
        self.kws_conv2 = ai8x.FusedConv1dReLU(64, 96, 3, 
                                              stride=1, padding=0,
                                              bias=bias, **kwargs)
        # T: 28 F : 96
        self.kws_conv3 = ai8x.FusedAvgPoolConv1dReLU(96, 100, 3, 
                                                     stride=1, padding=1,
                                                     bias=bias, **kwargs)
        # T : 14 F: 100
        self.kws_conv4 = ai8x.FusedMaxPoolConv1dReLU(100, 64, 6, 
                                                     stride=1, padding=1,
                                                     bias=bias, **kwargs)
        # T : 2 F: 128
        self.fc = ai8x.Linear(256, num_classes, bias=bias, wide=True, **kwargs)

    def forward(self, x):  # pylint: disable=arguments-differ
        """Forward prop"""
        # Run CNN
        x = self.voice_conv1(x)
        x = self.voice_conv2(x)
        x = self.drop(x)
        x = self.voice_conv3(x)
        x = self.voice_conv4(x)
        x = self.drop(x)
        x = self.kws_conv1(x)
        x = self.kws_conv2(x)
        x = self.drop(x)
        x = self.kws_conv3(x)
        x = self.kws_conv4(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)

        return x
The CNN input is 128x128=16384 8-bit signed speech samples.

试试烧录试kws20_v3

成功。

在编译烧录之前一定注意，要先make distclean 一下，不然会出问题的

尝试烧录 work15

cd /E/MAX78000/voice_light/work15/work15/kws20_demo/

报错喽

尝试烧录kws20_demo-riscv

$ cd /E/MAX78000/MAXSDK/Examples/MAX78000/CNN/kws20_demo-riscv/