README.md

metadata

title: RTMDet-Ins Tiny
subtitle: Real-time instance segmentation
category: Vision AI
model_type:
  - Instance Segmentation
license: apache-2.0
code: https://github.com/open-mmlab/mmdetection/tree/main/configs/rtmdet
tags:
  - robotics-ai-suite
  - vision-ai
  - chipset:ptl
thumbnail: assets/thumbnail.png

RTMDet-Ins Tiny instance segmentation model, a Geti™ build of RTMDet Instance Tiny converted to OpenVINO™ IR with FP16 weights. It maps an input image to per-instance masks and bounding boxes. Model weights are hosted in the source repository OpenVINO/rtmdet_inst_tiny-fp16-ov.

How to Use

1. Install required packages:

pip install openvino-model-api[huggingface]

2. Run model inference:

import cv2
from model_api.models import Model
from model_api.visualizer import Visualizer

model = Model.from_pretrained("OpenVINO/rtmdet_inst_tiny-fp16-ov")
image = cv2.imread("image.jpg")
result = model(image)
vis = Visualizer().render(image, result)
cv2.imwrite("output.jpg", vis)

Legal information

The original model is distributed under the Apache-2.0 license. More details can be found in the original model repository.