PG-StreetParse-M - a computer-vision model on Pictograph

Open in task arch mAP license

View on Pictograph · Pictograph Research · Instance Segmentation · RF-DETR Seg Medium · FP32 · Creative Commons Attribution-NoDerivatives 4.0

Overview

This is an instance segmentation model built on RF-DETR Seg Medium, trained on the A2D2 dataset. It expects 432x432 input and runs in FP32 precision. The ONNX weights are in this repo; run them with the Pictograph SDK (below) or open the model on Pictograph to test it in-browser, call the hosted API, or deploy it as an always-on endpoint.

Performance

Headline: 18.9% mAP.

Metric Value
mAP 18.9%
mAP@50 36.8%

Classes

Class index matches the model's output order.

# Class
0 car
1 pedestrian
2 truck
3 small vehicle
4 utility vehicle
5 bicycle

Training

Setting Value
Base dataset A2D2
Dataset size 12,758 images
Input size 432x432
Epochs 10
Batch size 4
Learning rate 0.0002
Model size medium
Precision FP32
Version 1.0.0

Use this model

The weights ship as ONNX (pg-streetparse-m.onnx) with a config.json. The Pictograph SDK applies the model's exact pre/post-processing for you:

Pictograph SDK

pip install "pictograph[inference]"
from huggingface_hub import hf_hub_download
from pictograph import load_model, InstanceSegmentationModel

onnx = hf_hub_download("pictograph/pg-streetparse-m", "pg-streetparse-m.onnx")
config = hf_hub_download("pictograph/pg-streetparse-m", "config.json")

model: InstanceSegmentationModel = load_model(onnx, config, task="instance_segmentation")
result = model.predict("photo.jpg")   # InstanceSegmentationResult
for p in result.polygons:              # instances whose mask polygonized
    b = p.bounding_box
    ring = p.polygon.paths[0]          # outer ring: [{'x','y'}, ...]
    print(f"{p.name} {p.confidence:.2f} {len(ring)}-pt mask "
          f"box=({b.x:.0f},{b.y:.0f},{b.w:.0f},{b.h:.0f})")

Example output (illustrative; your exact values depend on the image):

car 0.91 48-pt mask box=(118,86,140,210)
pedestrian 0.87 52-pt mask box=(120,250,132,300)
Raw ONNX Runtime (no SDK)
from huggingface_hub import hf_hub_download
import onnxruntime as ort

onnx = hf_hub_download("pictograph/pg-streetparse-m", "pg-streetparse-m.onnx")
sess = ort.InferenceSession(onnx, providers=["CPUExecutionProvider"])
inp = sess.get_inputs()[0]
print(inp.name, inp.shape)   # NCHW float32; input size + normalization in config.json
# outputs = sess.run(None, {inp.name: preprocessed_batch})
# Decoding is architecture-specific; the Pictograph SDK (above) does it for you.

License

Released under Creative Commons Attribution-NoDerivatives 4.0, the license of its training data, A2D2. Commercial use is permitted with attribution: when you use this model, please credit Audi AG (Geyer et al., 2020).

Citation

This model uses the RF-DETR Seg Medium architecture:

@inproceedings{robinson2026rfdetr,
  title     = {RF-DETR: Real-Time Detection Transformer},
  author    = {Robinson, Isaac and Robicheaux, Peter and Popov, Matvei and Ramanan, Deva and Peri, Neehar},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2026},
  url       = {https://arxiv.org/abs/2511.09554}
}

It was trained on A2D2, from:

@article{geyer2020a2d2,
  title = {{A2D2}: {Audi Autonomous Driving Dataset}},
  author = {Geyer, Jakob and Kassahun, Yohannes and Mahmudi, Mentar and Ricou, Xavier and Durgesh, Rupesh and Chung, Andrew S. and Hauswald, Lorenz and Pham, Viet Hoang and M{\"u}hlegg, Maximilian and Dorn, Sebastian and Fernandez, Tiffany and J{\"a}nicke, Martin and Mirashi, Sudesh and Savani, Chiragkumar and Sturm, Martin and Vorobiov, Oleksandr and Oelker, Martin and Garreis, Sebastian and Schuberth, Peter},
  journal = {arXiv preprint arXiv:2004.06320},
  year = {2020}
}

Trained and published with Pictograph - annotate, train, and deploy from one API.

Downloads last month
17
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for pictograph/pg-streetparse-m

Finetuned
(6)
this model

Dataset used to train pictograph/pg-streetparse-m

Papers for pictograph/pg-streetparse-m

Evaluation results