qengineering/lffd-mnn-jetson-nano

Face detection with MNN on a Jetson Nano

LFFD face detection Jetson Nano

LFFD face detection with the MNN framework.

Paper: https://arxiv.org/pdf/1904.10633.pdf

Special made for a Jetson Nano see Q-engineering deep learning examples

---

Benchmark.

Model	framework	model	size	mAP	Jetson Nano 2015 MHz	RPi 4 64-OS 1950 MHz
Ultra-Light-Fast	ncnn	slim-320	320x240	67.1	- FPS	26 FPS
Ultra-Light-Fast	ncnn	RFB-320	320x240	69.8	- FPS	23 FPS
Ultra-Light-Fast	MNN	slim-320	320x240	67.1	70 FPS	65 FPS
Ultra-Light-Fast	MNN	RFB-320	320x240	69.8	60 FPS	56 FPS
Ultra-Light-Fast	OpenCV	slim-320	320x240	67.1	48 FPS	40 FPS
Ultra-Light-Fast	OpenCV	RFB-320	320x240	69.8	43 FPS	35 FPS
Ultra-Light-Fast + Landmarks	ncnn	slim-320	320x240	67.1	50 FPS	24 FPS
LFFD	ncnn	5 stage	320x240	88.6	16.4 FPS	4.85 FPS
LFFD	ncnn	8 stage	320x240	88.6	11.7 FPS	3.45 FPS
LFFD	MNN	5 stage	320x240	88.6	2.6 FPS	2.17 FPS
LFFD	MNN	8 stage	320x240	88.6	1.8 FPS	1.49 FPS

---

Dependencies.

To run the application, you have to:

• The Alibaba's MNN framework installed. (https://qengineering.eu/install-mnn-on-jetson-nano.html)
  
• Code::Blocks installed. ($ sudo apt-get install codeblocks)

---

Installing the app.

To extract and run the network in Code::Blocks
$ mkdir MyDir
$ cd MyDir
$ wget https://github.com/Qengineering/LFFD-MNN-Raspberry-Pi-4/archive/refs/heads/main.zip
$ unzip -j master.zip
Remove master.zip, LICENSE and README.md as they are no longer needed.
$ rm master.zip
$ rm LICENSE
$ rm README.md

Your MyDir folder must now look like this:
images folder
Walks2.mp4
FaceDetection_LFFD_MNN.cpb
main.cpp
LFFD_MNN.h
LFFD_MNN.cpp
symbol_10_320_20L_5scales_v2_deploy.mnn
symbol_10_560_25L_8scales_v1_deploy.mnn

---

Running the app.

To run the application load the project file FaceDetection_LFFD_MNN.cbp in Code::Blocks.
Next, follow the instructions at Hands-On.

lffd-mnn-jetson-nano's Issues

How to run in CUDA mode?

Hi,

the code use cpu mode, how to run in cuda mode with MNN?

Thank you.

Can you share onnx model

Hi,

Can you share Ultra light onnx model? or white paper so that i can reproduce in pytorch

Thank you.

Did you run MNN as gpu mode or cpu mode?

Hi,

Did you run MNN as gpu mode or cpu mode in Raspberry Pi 4?

By the way, is FPS including bounding box regression and nms?

Vulkan backend not working with MNN

While trying to run benchmark.cpp utilizing the Vulkan backend as ./benchmark.out /home/ubuntu/MNN/models 1000 10 7 setting forward = MNN_FORWARD_VULKAN, I get the error Can't Find type=7 backend, use 0 instead even though I had built MNN following the instructions in here which also builds for the Vulkan backend setting -DMNN_VULKAN=true. I am working on an NVIDIA Jetson with Jetpack version 5.0.1.