pip install MNN on Raspberry pi 4 not work #1051

nakarin · 2020-08-12T11:09:30Z

I'd like to install MNN (Python) for RPi 4 by pip install MNN but not work.
Have anyone can solved this?

Thanks.

Ratansairohith · 2021-01-26T08:35:58Z

@nakarin Hi are you able to install it on raspberry pi 4? if yes , please let me know how to do it.
-Thank you in advance.

Co2Link · 2021-02-12T05:55:43Z

@Ratansairohith
Are you able to install it on rpi 4?

Ratansairohith · 2021-02-17T15:29:52Z

@ling9601 Nope i was unable to install it on rpi 4. If you find a way please let me know.

Co2Link · 2021-02-17T16:06:09Z

yes, I am not at home now. I will share the installation tomorrow

Co2Link · 2021-02-18T01:44:28Z

@Ratansairohith
The installation was tested on RP4b with the latest RP OS.

Try the following step to build the wheel and install it.

install dependency for compile

sudo apt-get install cmake libprotobuf-dev protobuf-compiler

get the source code

git clone https://github.com/alibaba/MNN

According to [this],(RangiLyu/nanodet#92) use 1.0.0 instead of the latest version (I tested that 1.1.3 is faster and the result is the same as 1.0.0, also mutithread in 1.1.3 can be used but not in 1.1.0)

git checkout 1.1.3

compile preparation

cd /path/to/MNN
./schema/generate.sh
mkdir pymnn_build

Build dependency for python wheel building

If we build MNNConvert, the follow error will show up(can't find any fix about this)

[100%] Linking CXX executable ../../MNNConvert
/usr/bin/ld: /usr/local/lib/libprotobuf.a(arena.o): in function google::protobuf::internal::ArenaImpl::Init(bool)': arena.cc:(.text+0x3ac): undefined reference to __atomic_fetch_add_8'
collect2: error: ld returned 1 exit status

so we dont build the MNNConvert. change the following lines

build_deps.py
...
    elif IS_LINUX:
        os.system('cmake -DMNN_BUILD_CONVERTER=on -DMNN_BUILD_TRAIN=ON -DCMAKE_BUILD_TYPE=Release\
            -DMNN_BUILD_SHARED_LIBS=OFF -DMNN_AAPL_FMWK=OFF -DMNN_SEP_BUILD=OFF\
            -DMNN_USE_THREAD_POOL=OFF .. && make MNN MNNTrain MNNConvert  -j4')
...

to

build_deps.py
...
    elif IS_LINUX:
        os.system('cmake -DMNN_BUILD_CONVERTER=on -DMNN_BUILD_TRAIN=ON -DCMAKE_BUILD_TYPE=Release\
            -DMNN_BUILD_SHARED_LIBS=OFF -DMNN_AAPL_FMWK=OFF -DMNN_SEP_BUILD=OFF\
            -DMNN_USE_THREAD_POOL=OFF .. && make MNN MNNTrain -j4')
...

use build_deps.py to build dependency

cd pymnn/pip_package
python build_deps.py

Build wheel

change platform, modify the following line

pymnn/pip_package/build_wheel.py
...
    if IS_LINUX:
        os.system('python setup.py bdist_wheel --plat-name=manylinux1_x86_64')
...

to

pymnn/pip_package/build_wheel.py
...
    if IS_LINUX:
        os.system('python setup.py bdist_wheel --plat-name=manylinux2014_armv7l')
...

don't build _tools, comment out the following lines

pymnn/pip_package/setup.py
...
    tools = Extension("_tools",\
                    libraries=tools_libraries,\
                    sources=tools_sources,\
                    language='c++',\
                    extra_compile_args=tools_compile_args + extra_compile_args,\
                    include_dirs=tools_include_dirs,\
                    library_dirs=tools_library_dirs,\
                    extra_link_args=tools_extra_link_args +tools_link_args\
                        + [make_relative_rpath('lib')])
    extensions.append(tools)
...

build wheel

python build_wheel.py

Install wheel

pip install pymnn/pip_package/dist/MNN-1.1.3-cp37-cp37m-manylinux2014_armv7l.whl

Test MNN installation

import MNN

Beacuse we did not build the _tools, the following error will show up

>>> import MNN
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/home/pi/.virtualenvs/mnn/lib/python3.7/site-packages/MNN/__init__.py", line 9, in <module>
    from . import tools
  File "/home/pi/.virtualenvs/mnn/lib/python3.7/site-packages/MNN/tools/__init__.py", line 1, in <module>
    from . import mnn, mnnops, mnnquant, mnnconvert 
  File "/home/pi/.virtualenvs/mnn/lib/python3.7/site-packages/MNN/tools/mnnquant.py", line 8, in <module>
    import _tools as Tools
ModuleNotFoundError: No module named '_tools'

in order the silent this error, comment out the following line

/home/pi/.virtualenvs/mnn/lib/python3.7/site-packages/MNN/__init__.py
...
from . import tools
...

then test import MNN again, it should be all done now

Ratansairohith · 2021-02-18T16:37:25Z

@ling9601 thank you very much for your detailed explaination! I will try it out this week and get back to you if i had any trouble.

fly-studio · 2021-05-25T15:04:59Z

modify `build_wheel.py` on aarch64 os (or openfans) of raspberry pi

# manylinux2014_armv7l to manylinux2014_aarch64
if IS_LINUX:
        comm_args += ' --plat-name=manylinux2014_aarch64'
...

# python to python3
os.system('python3 setup.py bdist_wheel %s' % comm_args)

build wheel as version 1.1.7

python3 build_wheel.py --version 1.1.7

after install `MNN-1.1.7-cp37-cp37m-manylinux2014_aarch64.whl`

Modify vim /usr/local/lib/python3.7/dist-packages/MNN/__init__.py

comment

# from .version import __version__
...
# from . import tools

mosheliv · 2021-06-17T22:57:24Z

I wonder if you can share the speed you get on the rpi with MNN? FPS for the models you use?

GuoJingtao-1997 · 2022-09-03T09:08:54Z

For MNN-2.0.0 in raspberry pi 4 with kernel version 5.10.92-v7l+, only need to modify the build_wheel.py as follows:

pymnn/pip_package/build_wheel.py
...
    if IS_LINUX:
        os.system('python setup.py bdist_wheel --plat-name=manylinux2014_armv7l')
...

wangzhaode · 2023-02-15T07:53:37Z

@Ratansairohith The installation was tested on RP4b with the latest RP OS.

Try the following step to build the wheel and install it.

install dependency for compile

sudo apt-get install cmake libprotobuf-dev protobuf-compiler

get the source code

git clone https://github.com/alibaba/MNN

According to [this],(RangiLyu/nanodet#92) use 1.0.0 instead of the latest version (I tested that 1.1.3 is faster and the result is the same as 1.0.0, also mutithread in 1.1.3 can be used but not in 1.1.0)

git checkout 1.1.3

compile preparation

cd /path/to/MNN
./schema/generate.sh
mkdir pymnn_build

Build dependency for python wheel building

If we build MNNConvert, the follow error will show up(can't find any fix about this)

[100%] Linking CXX executable ../../MNNConvert
/usr/bin/ld: /usr/local/lib/libprotobuf.a(arena.o): in function google::protobuf::internal::ArenaImpl::Init(bool)': arena.cc:(.text+0x3ac): undefined reference to __atomic_fetch_add_8'
collect2: error: ld returned 1 exit status

so we dont build the MNNConvert. change the following lines

build_deps.py
...
    elif IS_LINUX:
        os.system('cmake -DMNN_BUILD_CONVERTER=on -DMNN_BUILD_TRAIN=ON -DCMAKE_BUILD_TYPE=Release\
            -DMNN_BUILD_SHARED_LIBS=OFF -DMNN_AAPL_FMWK=OFF -DMNN_SEP_BUILD=OFF\
            -DMNN_USE_THREAD_POOL=OFF .. && make MNN MNNTrain MNNConvert  -j4')
...

to

build_deps.py
...
    elif IS_LINUX:
        os.system('cmake -DMNN_BUILD_CONVERTER=on -DMNN_BUILD_TRAIN=ON -DCMAKE_BUILD_TYPE=Release\
            -DMNN_BUILD_SHARED_LIBS=OFF -DMNN_AAPL_FMWK=OFF -DMNN_SEP_BUILD=OFF\
            -DMNN_USE_THREAD_POOL=OFF .. && make MNN MNNTrain -j4')
...

use build_deps.py to build dependency

cd pymnn/pip_package
python build_deps.py

Build wheel

change platform, modify the following line

pymnn/pip_package/build_wheel.py
...
    if IS_LINUX:
        os.system('python setup.py bdist_wheel --plat-name=manylinux1_x86_64')
...

to

pymnn/pip_package/build_wheel.py
...
    if IS_LINUX:
        os.system('python setup.py bdist_wheel --plat-name=manylinux2014_armv7l')
...

don't build _tools, comment out the following lines

pymnn/pip_package/setup.py
...
    tools = Extension("_tools",\
                    libraries=tools_libraries,\
                    sources=tools_sources,\
                    language='c++',\
                    extra_compile_args=tools_compile_args + extra_compile_args,\
                    include_dirs=tools_include_dirs,\
                    library_dirs=tools_library_dirs,\
                    extra_link_args=tools_extra_link_args +tools_link_args\
                        + [make_relative_rpath('lib')])
    extensions.append(tools)
...

build wheel

python build_wheel.py

Install wheel

pip install pymnn/pip_package/dist/MNN-1.1.3-cp37-cp37m-manylinux2014_armv7l.whl

Test MNN installation

import MNN

Beacuse we did not build the _tools, the following error will show up

>>> import MNN
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/home/pi/.virtualenvs/mnn/lib/python3.7/site-packages/MNN/__init__.py", line 9, in <module>
    from . import tools
  File "/home/pi/.virtualenvs/mnn/lib/python3.7/site-packages/MNN/tools/__init__.py", line 1, in <module>
    from . import mnn, mnnops, mnnquant, mnnconvert 
  File "/home/pi/.virtualenvs/mnn/lib/python3.7/site-packages/MNN/tools/mnnquant.py", line 8, in <module>
    import _tools as Tools
ModuleNotFoundError: No module named '_tools'

in order the silent this error, comment out the following line

/home/pi/.virtualenvs/mnn/lib/python3.7/site-packages/MNN/__init__.py
...
from . import tools
...

then test import MNN again, it should be all done now

Don't have pre-build python whl for raspberry. Suggest this method.

mosheliv · 2023-02-15T22:26:09Z

Hi,
Thanks for that. I have moved to other products since this was opened, but would like to comment that this installs 1.1.3 while the cutting edge is 2.3 and this is a pretty awkward process. As rpi is probably the most used SBC in the world, you would think it deserves better support.
Just my thoughts.

Best regards,
Moshe

jasonmatos23-git mentioned this issue Mar 9, 2022

Faster mono depth jasonmatos23-git/DepthPerceptionHapticSystem#22

Merged

wangzhaode closed this as completed Feb 15, 2023

wangzhaode self-assigned this Feb 15, 2023

wangzhaode added building Pymnn mnn python Raspberry Pi labels Feb 15, 2023

wangzhaode mentioned this issue Feb 23, 2023

RK3588编译MNN的whl包 #2221

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

pip install MNN on Raspberry pi 4 not work #1051

pip install MNN on Raspberry pi 4 not work #1051

nakarin commented Aug 12, 2020

Ratansairohith commented Jan 26, 2021

Co2Link commented Feb 12, 2021

Ratansairohith commented Feb 17, 2021

Co2Link commented Feb 17, 2021

Co2Link commented Feb 18, 2021

Ratansairohith commented Feb 18, 2021

fly-studio commented May 25, 2021 •

edited

Loading

mosheliv commented Jun 17, 2021

GuoJingtao-1997 commented Sep 3, 2022

wangzhaode commented Feb 15, 2023

mosheliv commented Feb 15, 2023

pip install MNN on Raspberry pi 4 not work #1051

pip install MNN on Raspberry pi 4 not work #1051

Comments

nakarin commented Aug 12, 2020

Ratansairohith commented Jan 26, 2021

Co2Link commented Feb 12, 2021

Ratansairohith commented Feb 17, 2021

Co2Link commented Feb 17, 2021

Co2Link commented Feb 18, 2021

Ratansairohith commented Feb 18, 2021

fly-studio commented May 25, 2021 • edited Loading

modify build_wheel.py on aarch64 os (or openfans) of raspberry pi

build wheel as version 1.1.7

after install MNN-1.1.7-cp37-cp37m-manylinux2014_aarch64.whl

mosheliv commented Jun 17, 2021

GuoJingtao-1997 commented Sep 3, 2022

For MNN-2.0.0 in raspberry pi 4 with kernel version 5.10.92-v7l+, only need to modify the build_wheel.py as follows:

wangzhaode commented Feb 15, 2023

mosheliv commented Feb 15, 2023

fly-studio commented May 25, 2021 •

edited

Loading

modify `build_wheel.py` on aarch64 os (or openfans) of raspberry pi

after install `MNN-1.1.7-cp37-cp37m-manylinux2014_aarch64.whl`