PG-COCO-Pose

Pictograph Research · Keypoint detection · Trained 6h ago · Custom license

Use this model

PG-COCO-Pose

Environment

Weights

ONNX SafeTensors PyTorch ExecuTorch TensorRT Engine

Precision

FP32 FP16

Model weights147 MB Model config

from pictograph import Client, get_model, KeypointModel, KeypointResult

client = Client(api_key="pk_live_...")   # Settings -> API Keys

# Downloads + caches the weights on first use
model: KeypointModel = get_model(
    name="PG-COCO-Pose",
    task="keypoint_detection",
    format="onnx",
    client=client,
)
result: KeypointResult = model.predict(image="photo.jpg")

for instance in result.instances:   # joints grouped by instance_id
    for joint in instance:
        p = joint.keypoint
        print(joint.name, round(p.x), round(p.y))

from pictograph import load_model, KeypointModel, KeypointResult

# Download the weights + config with the buttons above
model: KeypointModel = load_model(
    weights="/path/to/weights.onnx",
    config="/path/to/config.json",
    task="keypoint_detection",
    format="onnx",
    device="auto",
)
result: KeypointResult = model.predict(image="photo.jpg")

for instance in result.instances:   # joints grouped by instance_id
    for joint in instance:
        p = joint.keypoint
        print(joint.name, round(p.x), round(p.y))

Deploy this model to Pictograph for an always-on, autoscaling /predict endpoint. Then call it from anywhere:

curl -X POST "https://workflows.pictograph.io/your-endpoint/predict" \
  -H "Authorization: Bearer pk_deploy_..." \
  -F "file=@frame.jpg"

from pictograph import DeploymentClient, KeypointResult

client = DeploymentClient(
    endpoint="https://workflows.pictograph.io/your-endpoint/predict",
    api_key="pk_deploy_...",  # from your deployment's settings
    task="keypoint_detection",
)
result: KeypointResult = client.infer(image="frame.jpg")

for instance in result.instances:   # joints grouped by instance_id
    for joint in instance:
        p = joint.keypoint
        print(joint.name, round(p.x), round(p.y))

pictograph deployments predict \
  <deployment-id> \
  frame.jpg \
  --token pk_deploy_... \
  --endpoint "https://workflows.pictograph.io/your-endpoint/predict"

Model Card

PG-COCO-Pose

A keypoint detection model (RF-DETR Keypoint Preview), locating each person and its 17 keypoints, scoring 73.2% OKS.

Pictograph Research · Keypoint Detection · RF-DETR Keypoint Preview · FP32 · a custom license · Public

Overview

This is a keypoint detection model built on RF-DETR Keypoint Preview, trained on the COCO 2017 Pose dataset. It expects 576x576 input and runs in FP32 precision. It finds each person and its 17 keypoints: the Skeleton section lists them in output order, with the joints each connects to.

Performance

Headline: 73.2% OKS.

Metric	Value
OKS	73.2%
OKS@50	89.1%
OKS@75	79.2%
Recall	78.8%

OKS is COCO's keypoint AP: the average precision over object keypoint similarity (OKS) thresholds 0.50 to 0.95. OKS@50 and OKS@75 are the AP at one threshold; Recall is the average recall over 0.50 to 0.95.

Skeleton

Each object the model finds is one instance: its keypoints share an instance_id, are named for their joint and carry their own confidence. The keypoint index is the model's output order.

#	Keypoint	Connects to
0	nose	left_eye, right_eye
1	left_eye	right_eye, nose, left_ear
2	right_eye	left_eye, nose, right_ear
3	left_ear	left_eye, left_shoulder
4	right_ear	right_eye, right_shoulder
5	left_shoulder	left_hip, right_shoulder, left_elbow, left_ear
6	right_shoulder	right_hip, left_shoulder, right_elbow, right_ear
7	left_elbow	left_shoulder, left_wrist
8	right_elbow	right_shoulder, right_wrist
9	left_wrist	left_elbow
10	right_wrist	right_elbow
11	left_hip	left_knee, right_hip, left_shoulder
12	right_hip	right_knee, left_hip, right_shoulder
13	left_knee	left_ankle, left_hip
14	right_knee	right_ankle, right_hip
15	left_ankle	left_knee
16	right_ankle	right_knee

Training

Setting	Value
Base dataset	COCO 2017 Pose
Export	COCO 2017 Pose-select
Dataset size	10,799 images
Input size	576x576
Epochs	12
Batch size	4
Learning rate	0.0001
Model size	preview
Precision	FP32
Version	1.0.0

Use this model

Run inference with the Pictograph SDK:

from pictograph import Client, get_model, KeypointModel, KeypointResult

client = Client(api_key="pk_live_...")  # Settings -> API Keys

# Downloads + caches the weights on first use
model: KeypointModel = get_model(
    name="PG-COCO-Pose",
    task="keypoint_detection",
    format="onnx",
    precision="fp32",
    device="cpu",
    client=client,
)
result: KeypointResult = model.predict(image="photo.jpg")
print(result)

# Fully offline (no API key) once you have the weights + config.json
from pictograph import load_model, KeypointModel, KeypointResult

model: KeypointModel = load_model(
    "/path/to/weights.onnx",
    "/path/to/config.json",
    task="keypoint_detection",
    format="onnx",
)
result: KeypointResult = model.predict(image="photo.jpg")

Full inference guide: local inference docs.
REST + CLI: models API reference.
Deploy it as an always-on endpoint: deployments.

License

Released under a custom license.

Download the model files

Exports to ONNX · 147 MB · FP32. Sign in to download the weights and config, or pull it from the SDK with the Use Model snippet.

COCO 2017 Pose

Pictograph Research

69,730 images · 0 classes

Custom License Other

Non-commercial use only. Trained on COCO 2017 Pose, whose images are COCO's: the COCO Consortium does not own their copyright; each image comes from Flickr under its own license, recorded per image in COCO's annotation files, and most of them (68.9% of train2017) are Creative Commons NonCommercial. COCO's annotations are CC BY 4.0, the COCO Consortium. The RF-DETR Keypoint base model is Apache 2.0 (Roboflow). Cite Lin et al., Microsoft COCO: Common Objects in Context (ECCV 2014).

Join the discussion

Comments and reactions live in the app.

Build your first vision tool

$5 of free compute every month. No card required.

Start free View pricing