东哥科技，专注科技研发，wx交流：dg_i688

我的项目代码

https://github.com/cdmstrong/ncnn_on_esp32s3

下载ncnn

git clone https://github.com/Tencent/ncnn.git

安装idf 环境

这里直接按官网的可执行文件来就好了，直接安装完成。

参考：https://docs.espressif.com/projects/esp-idf/zh_CN/latest/esp32/get-started/windows-setup.html#get-started-windows-first-steps

安装完成打开idf 的cmd可以打印出idf命令

编译ncnn

打开idf终端，进入到目录
新建一个目录用于存放编译文件build-s3

需要创建一个esp32s3的交叉编译配置文件, 在toolchains下

输入下面的内容，主要是去除一些不支持的内容和内存优化
去除 bf16，int8，图像处理，文件加载模型，多线程，平台相关功能，C接口，c++ rtti exception
去除 mnist 模型中用不到的算子

set(CMAKE_SYSTEM_NAME freertos)
set(CMAKE_SYSTEM_PROCESSOR xtensa-esp32s3)include($ENV{IDF_PATH}/tools/cmake/toolchain-esp32s3.cmake)set(CMAKE_TRY_COMPILE_TARGET_TYPE STATIC_LIBRARY)set(CMAKE_FIND_ROOT_PATH_MODE_PROGRAM NEVER)
set(CMAKE_FIND_ROOT_PATH_MODE_LIBRARY ONLY)
set(CMAKE_FIND_ROOT_PATH_MODE_INCLUDE ONLY)
set(CMAKE_FIND_ROOT_PATH_MODE_PACKAGE ONLY)# cache flags
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS}" CACHE STRING "c flags")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}" CACHE STRING "c++ flags")option(NCNN_INSTALL_SDK "" ON)
option(NCNN_PIXEL_ROTATE "" OFF)
option(NCNN_PIXEL_AFFINE "" OFF)
option(NCNN_PIXEL_DRAWING "" OFF)
option(NCNN_BUILD_BENCHMARK "" OFF)
option(NCNN_BUILD_TESTS "" OFF)
option(NCNN_BUILD_TOOLS "" OFF)
option(NCNN_BUILD_EXAMPLES "" OFF)
option(NCNN_DISABLE_RTTI "" ON)
option(NCNN_DISABLE_EXCEPTION "" ON)
option(NCNN_DISABLE_PIC "" ON)
option(NCNN_BF16 "" OFF)
option(NCNN_INT8 "" OFF)
option(NCNN_THREADS "" OFF)
option(NCNN_OPENMP "" OFF)
option(NCNN_STDIO "" OFF)
option(NCNN_STRING "" OFF)
option(NCNN_PLATFORM_API "" OFF)
option(NCNN_RUNTIME_CPU "" OFF)option(WITH_LAYER_absval "" OFF)
option(WITH_LAYER_argmax "" OFF)
option(WITH_LAYER_batchnorm "" OFF)
option(WITH_LAYER_bias "" OFF)
option(WITH_LAYER_bnll "" OFF)
option(WITH_LAYER_concat "" OFF)
option(WITH_LAYER_convolution "" ON)
option(WITH_LAYER_crop "" OFF)
option(WITH_LAYER_deconvolution "" OFF)
option(WITH_LAYER_dropout "" OFF)
option(WITH_LAYER_eltwise "" OFF)
option(WITH_LAYER_elu "" OFF)
option(WITH_LAYER_embed "" OFF)
option(WITH_LAYER_exp "" OFF)
option(WITH_LAYER_flatten "" ON)
option(WITH_LAYER_innerproduct "" ON)
option(WITH_LAYER_input "" ON)
option(WITH_LAYER_log "" OFF)
option(WITH_LAYER_lrn "" OFF)
option(WITH_LAYER_memorydata "" ON)
option(WITH_LAYER_mvn "" OFF)
option(WITH_LAYER_pooling "" ON)
option(WITH_LAYER_power "" OFF)
option(WITH_LAYER_prelu "" OFF)
option(WITH_LAYER_proposal "" OFF)
option(WITH_LAYER_reduction "" OFF)
option(WITH_LAYER_relu "" ON)
option(WITH_LAYER_reshape "" ON)
option(WITH_LAYER_roipooling "" OFF)
option(WITH_LAYER_scale "" OFF)
option(WITH_LAYER_sigmoid "" OFF)
option(WITH_LAYER_slice "" OFF)
option(WITH_LAYER_softmax "" OFF)
option(WITH_LAYER_split "" ON)
option(WITH_LAYER_spp "" OFF)
option(WITH_LAYER_tanh "" OFF)
option(WITH_LAYER_threshold "" OFF)
option(WITH_LAYER_tile "" OFF)
option(WITH_LAYER_rnn "" OFF)
option(WITH_LAYER_lstm "" OFF)
option(WITH_LAYER_binaryop "" ON)
option(WITH_LAYER_unaryop "" OFF)
option(WITH_LAYER_convolutiondepthwise "" OFF)
option(WITH_LAYER_padding "" ON)
option(WITH_LAYER_squeeze "" OFF)
option(WITH_LAYER_expanddims "" OFF)
option(WITH_LAYER_normalize "" OFF)
option(WITH_LAYER_permute "" OFF)
option(WITH_LAYER_priorbox "" OFF)
option(WITH_LAYER_detectionoutput "" OFF)
option(WITH_LAYER_interp "" OFF)
option(WITH_LAYER_deconvolutiondepthwise "" OFF)
option(WITH_LAYER_shufflechannel "" OFF)
option(WITH_LAYER_instancenorm "" OFF)
option(WITH_LAYER_clip "" OFF)
option(WITH_LAYER_reorg "" OFF)
option(WITH_LAYER_yolodetectionoutput "" OFF)
option(WITH_LAYER_quantize "" OFF)
option(WITH_LAYER_dequantize "" OFF)
option(WITH_LAYER_yolov3detectionoutput "" OFF)
option(WITH_LAYER_psroipooling "" OFF)
option(WITH_LAYER_roialign "" OFF)
option(WITH_LAYER_packing "" ON)
option(WITH_LAYER_requantize "" OFF)
option(WITH_LAYER_cast "" ON)
option(WITH_LAYER_hardsigmoid "" OFF)
option(WITH_LAYER_selu "" OFF)
option(WITH_LAYER_hardswish "" OFF)
option(WITH_LAYER_noop "" OFF)
option(WITH_LAYER_pixelshuffle "" OFF)
option(WITH_LAYER_deepcopy "" OFF)
option(WITH_LAYER_mish "" OFF)
option(WITH_LAYER_statisticspooling "" OFF)
option(WITH_LAYER_swish "" OFF)
option(WITH_LAYER_gemm "" ON)
option(WITH_LAYER_groupnorm "" OFF)
option(WITH_LAYER_layernorm "" OFF)
option(WITH_LAYER_softplus "" OFF)
option(WITH_LAYER_gru "" OFF)
option(WITH_LAYER_multiheadattention "" OFF)
option(WITH_LAYER_gelu "" OFF)
option(WITH_LAYER_convolution1d "" OFF)
option(WITH_LAYER_pooling1d "" OFF)
option(WITH_LAYER_convolutiondepthwise1d "" OFF)
option(WITH_LAYER_convolution3d "" OFF)
option(WITH_LAYER_convolutiondepthwise3d "" OFF)
option(WITH_LAYER_pooling3d "" OFF)
option(WITH_LAYER_matmul "" OFF)
option(WITH_LAYER_deconvolution1d "" OFF)
option(WITH_LAYER_deconvolutiondepthwise1d "" OFF)
option(WITH_LAYER_deconvolution3d "" OFF)
option(WITH_LAYER_deconvolutiondepthwise3d "" OFF)# cmake -DCMAKE_TOOLCHAIN_FILE=../toolchains/esp32s3.toolchain.cmake -DCMAKE_BUILD_TYPE=Release ..

根据该 issue 的信息，需要开启 NCNN_DISABLE_PIC，解决最后链接失败的问题
https://github.com/espressif/esp-idf/issues/7359

进行编译, 我的是windows

linux根据需要调整
我这里用了make 工具，而不是vs编译

mkdir build-s3
cd build-s3
cmake -DCMAKE_TOOLCHAIN_FILE=../toolchains/esp32s3.toolchain.cmake -DCMAKE_BUILD_TYPE=Release  -G"Unix Makefiles" ..
make -j4
make install

cmake命令

make命令

将install改成ncnn

部署到esp32s3上

下载demo工程，这个是c3的，也差不多，修改下就好了
https://github.com/nihui/ncnn_on_esp32/tree/master

然后修改CMakelists.txt

set(CMAKE_SYSTEM_NAME freertos)
set(CMAKE_SYSTEM_PROCESSOR xtensa-esp32s3)

ncnn是linux平台编译的c3的，需要替换成你自己的
把刚刚编译的ncnn替换成项目的这个ncnn库

然后打开idf 的终端
设置目标平台
输入：

idf.py set-target esp32s3

有需要的也可以进行配置下：目前是不用配置

idf.py menuconfig

进行编译：

idf.py build

运行：这里可以用-p Port 指定串口名称，不用管他，系统会自动寻找可以用的

idf.py flash

监听输出结果

idf.py monitor

后续

后面根据需要部署自己的模型，建议在这个项目上进行修改，我会继续更新