CV / FCN ResNet

FCN8 ResNet-18

FCN-8s (Fully Convolutional Network) with ResNet-18 backbone performs real-time semantic segmentation with 19 Cityscapes classes through HailoRT inference.

2 downloads

Size

9.2 MB

Memory

4GB+

Precision

Hailo HEF / HailoRT

Choose the device you're using, the set up guide and documentation will update accordingly.

Platform

Inference Engine

Getting Started

Deploy

sudo docker run --rm \
  --name cm5-hailo-fcn8-resnet \
  --privileged \
  --net=host \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  -v /usr/lib/libhailort.so.5.1.1:/usr/lib/libhailort.so.5.1.1:ro \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-hailo10h-cv/fcn8_resnet_v1_18:latest \
  python web_detection.py --model_path model/fcn8_resnet_v1_18.hef --video_path video/test.mp4

REST API

Use the REST API to run inference. Copy the commands below.

Curl

curl -X POST "http://<Board_IP>:8000/api/models/fcn8_resnet/predict" \
  -F "file=@test.jpg"

Python

import requests

resp = requests.post(
    "http://<Board_IP>:8000/api/models/fcn8_resnet/predict",
    files={"file": open("test.jpg", "rb")},
    timeout=30,
)
print(resp.json())

Model Details

FCN8 ResNet-18 on reComputer R Series (CM5 + Hailo-10H)

FCN-8s (Fully Convolutional Network) with ResNet-18 backbone for semantic segmentation, running on Hailo-10H via HailoRT.

This page targets reComputer R Series (CM5 + Hailo-10H) with a PCIe Hailo-10H accelerator.

Model Info

Property	Value
Architecture	FCN-8s + ResNet-18
Task	Semantic Segmentation
Input	1024×1920×3 RGB
Output	1024×1920 class mask (19 classes)
Parameters	11.20M
mIoU (Cityscapes)	69.2% (hardware)
Source	Hailo Model Zoo

Cityscapes Classes

ID	Class	ID	Class	ID	Class
0	road	7	traffic sign	14	truck
1	sidewalk	8	vegetation	15	bus
2	building	9	terrain	16	train
3	wall	10	sky	17	motorcycle
4	fence	11	person	18	bicycle
5	pole	12	rider
6	traffic light	13	car

Hardware and Host Setup

Item	Value
Board	reComputer R Series with Raspberry Pi CM5
Accelerator	Hailo-10H over PCIe, exposed as `/dev/hailo0`
OS	Raspberry Pi OS Bookworm, aarch64
Host driver	`hailo-h10-all` apt package

bash

sudo apt update
sudo apt install hailo-h10-all -y
sudo reboot

# After reboot
hailortcli fw-control identify
ls /dev/hailo0

# Docker
curl -fsSL https://get.docker.com -o get-docker.sh
sudo sh get-docker.sh --mirror Aliyun
sudo systemctl enable docker
sudo systemctl start docker

Run With Demo Video

bash

sudo docker run --rm --privileged --net=host \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  -v /usr/lib/libhailort.so.5.1.1:/usr/lib/libhailort.so.5.1.1:ro \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-hailo10h-cv/fcn8_resnet_v1_18:latest \
  python web_detection.py --model_path model/fcn8_resnet_v1_18.hef --video_path video/test.mp4

Open http://<Board_IP>:8000 to view the web preview. The image includes the module source, demo video, HailoRT Python wheel, and HEF files listed below.

USB Camera Mode

bash

sudo docker run --rm --privileged --net=host \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  --device /dev/video0:/dev/video0 \
  -v /usr/lib/libhailort.so.5.1.1:/usr/lib/libhailort.so.5.1.1:ro \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-hailo10h-cv/fcn8_resnet_v1_18:latest \
  python web_detection.py --model_path model/fcn8_resnet_v1_18.hef --camera_id 0

HEF Files

HEF	Size	Notes
`fcn8_resnet_v1_18.hef`	9.2 MB	Semantic segmentation model

REST API

Prediction endpoint:

text

POST http://<Board_IP>:8000/api/models/fcn8_resnet/predict

Example image request:

bash

curl -X POST "http://<Board_IP>:8000/api/models/fcn8_resnet/predict" \
  -F "file=@test.jpg"

Common service endpoints:

Endpoint	Method	Purpose
`/`	GET	Web preview UI
`/api/models/fcn8_resnet/predict`	POST	Per-class pixel coverage (JSON)
`/api/video_feed`	GET	MJPEG preview stream

Development Notes

Source module: src/hailo10h_fcn8_resnet_v1_18/
Dockerfile: docker/hailo10h/fcn8_resnet_v1_18.dockerfile
Main service: web_detection.py wraps HailoRT inference, post-processing, MJPEG preview, and REST prediction.

Inputs and Outputs

Input: image (1024x1920 RGB). Output: 19-class semantic segmentation mask (Cityscapes).