Edge Device Ml Deployment Computer Vision Tools

There are 30 edge device ml deployment tools tracked. 1 score above 50 (established tier). The highest-rated is RangiLyu/nanodet at 50/100 with 6,170 stars.

Get all 30 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=computer-vision&subcategory=edge-device-ml-deployment&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

# Tool Score Tier
1 RangiLyu/nanodet

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model....
50
Established
2 PINTO0309/OpenVINO-YoloV3

YoloV3/tiny-YoloV3+RaspberryPi3/Ubuntu LaptopPC+NCS/NCS2+USB Camera+Python+OpenVINO
44
Emerging
3 dog-qiuqiu/MobileNet-Yolo

MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img,...
42
Emerging
4 Qengineering/Face-Recognition-Jetson-Nano

Recognize 2000+ faces on your Jetson Nano with database auto-fill and anti-spoofing
40
Emerging
5 Qengineering/YoloV7-ncnn-Raspberry-Pi-4

YoloV7 for a bare Raspberry Pi using ncnn.
37
Emerging
6 Qengineering/Face-Recognition-Raspberry-Pi-64-bits

Recognize 2000+ faces on your Raspberry Pi 4 with database auto-fill and...
37
Emerging
7 Qengineering/YoloV8-NPU

YoloV8 NPU for the RK3566/68/88

37
Emerging
8 Qengineering/Qengineering

Machine vision apps
35
Emerging
9 devolksbank/Raspberry-Pi-Movidius-Person-Detector

Raspberry Pi Movidius Neural Compute Stick person detector installer
33
Emerging
10 Qengineering/YoloV5-NPU

YoloV5 NPU for the RK3566/68/88
33
Emerging
11 Qengineering/Face-Recognition-with-Mask-Jetson-Nano

Recognize 2000+ faces on your Jetson Nano with additional mask detection,...
33
Emerging
12 Qengineering/YoloV8-ncnn-Raspberry-Pi-4

YoloV8 for a bare Raspberry Pi 4 or 5
33
Emerging
13 Qengineering/YoloX-Tracking-ncnn-RPi_64-bit

YoloX with tracking for a bare Raspberry Pi 4 using ncnn.
31
Emerging
14 nihui/ncnn-webassembly-yolov5

Deploy YOLOv5 in your web browser with ncnn and webassembly
31
Emerging
15 code2k13/rpipico_digit_classification

Identification of handwritten digit from images taken by a  OV7670 camera...
31
Emerging
16 Qengineering/YoloFastestV2-ncnn-Raspberry-Pi-4

YoloFastestV2 for a bare Raspberry Pi 4
31
Emerging
17 nihui/ncnn-webassembly-nanodet

Deploy nanodet, the super fast and lightweight object detection, in your web...
31
Emerging
18 Qengineering/YoloV6-ncnn-Raspberry-Pi-4

YoloV6 for a bare Raspberry Pi using ncnn.
29
Experimental
19 Qengineering/Traffic-Counter-RPi_64-bit

A fully functional traffic counter on a bare Raspberry Pi 4 with MQTT and...
29
Experimental
20 Qengineering/YoloV5-ncnn-Raspberry-Pi-4

YoloV5 for a bare Raspberry Pi 4
28
Experimental
21 Qengineering/YoloV10-NPU

YoloV10 NPU for the RK3566/68/88

27
Experimental
22 Qengineering/YoloV9-ncnn-Raspberry-Pi-4

YoloV9 for a bare Raspberry Pi 4/5

27
Experimental
23 EyecloudAi/openncc

OpenNCC Kit
27
Experimental
24 Qengineering/TensorFlow_Lite_Face_Mask_RPi_64-bits

Face mask detection on a bare Raspberry Pi 4 wit 32 or 64-bit OS
26
Experimental
25 nihui/ncnn-webassembly-scrfd

Deploy SCRFD, an efficient high accuracy face detection approach, in your...
26
Experimental
26 EyecloudAi/opennccframe

OpenNCC Frame
25
Experimental
27 nihui/ncnn-webassembly-portrait-segmentation

Portrait segmentation in your web browser with ncnn and webassembly
25
Experimental
28 Qengineering/GFPGAN-ncnn-Raspberry-Pi-4

GFPGAN face reconstruction with ncnn on a bare Raspberry Pi
24
Experimental
29 Qengineering/Head-Pose-ncnn-Raspberry-Pi-4

Ultra fast head pose estimation on a bare Raspberry Pi 4 at 20 FPS
21
Experimental
30 Qengineering/YoloV8-seg-NPU

YoloV8 segmentation NPU for the RK 3566/68/88
15
Experimental

Comparisons in this category

nanodet and ncnn-webassembly-nanodet (50 vs 31) ncnn-webassembly-nanodet and ncnn-webassembly-yolov5 (31 vs 31) YoloV7-ncnn-Raspberry-Pi-4 and YoloV8-ncnn-Raspberry-Pi-4 (37 vs 33) Face-Recognition-Jetson-Nano and Face-Recognition-Raspberry-Pi-64-bits (40 vs 37) YoloV8-ncnn-Raspberry-Pi-4 and YoloFastestV2-ncnn-Raspberry-Pi-4 (33 vs 31) Face-Recognition-Jetson-Nano and Face-Recognition-with-Mask-Jetson-Nano (40 vs 33) YoloV7-ncnn-Raspberry-Pi-4 and YoloV5-ncnn-Raspberry-Pi-4 (37 vs 28) YoloV7-ncnn-Raspberry-Pi-4 and YoloFastestV2-ncnn-Raspberry-Pi-4 (37 vs 31) YoloV8-ncnn-Raspberry-Pi-4 and YoloX-Tracking-ncnn-RPi_64-bit (33 vs 31) YoloV8-ncnn-Raspberry-Pi-4 and YoloV6-ncnn-Raspberry-Pi-4 (33 vs 29)