FFNet-40S

简介

Semantic segmentation for automotive street scenes.
FFNet‑40S is a "fuss‑free network" that segments street scene images with per‑pixel classes like road, sidewalk, and pedestrian. Trained on the Cityscapes dataset.

效果视频

规格与下载

技术细节

Model checkpoint:ffnet40S_dBBB_cityscapes_state_dict_quarts
Input resolution:2048x1024
Number of output classes:19
Number of parameters:13.9M
Model size (float):53.1 MB
Model size (w8a8):13.5 MB

应用领域

Automotive
Autonomous Driving
Camera

授权信息

Source Model: BSD-3-CLAUSE
Deployable Model: AI-HUB-MODELS-LICENSE