SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1812.08008 · 2018

OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

arXiv · PDF · Open in the Atlas

Code that ran

12 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 3 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1812.08008.json · badge: /api/ran/1812.08008.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Zero-nnkn/ml-utils community (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
daniegr/EfficientPose community (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
JohnnyHopp/Pose-Estimation-Part-Affinity-Field-Mobilenetv2- reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
CMU-Perceptual-Computing-Lab/openpose_train extension (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
conv_1x1_bn Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from zhoudaquan/rethinking_bottleneck_design
pointer only; the stored copy get_code serves, from zhoudaquan/rethinking_bottleneck_design, is pointer only (licence: NOASSERTION) · get_code("a0131fb70c267a9e")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv_bn Ran
ran; our contract draft was wrong, not the code
JohnnyHopp/Pose-Estimation-Part-Affinity-Field-Mobilenetv2-/20200307PAF/model/MobileNetV2.py
code served (permissive licence) · get_code("e087cbfa1e53486d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "inp": 3,
    "oup": 16,
    "stride": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
eswish Ran
ran on a synthesized input
daniegr/EfficientPose/utils/helpers.py
code served (permissive licence) · get_code("9aa84f03a1a82763")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf
from tensorflow.keras.backend import sigmoid, constant

# Create a small input tensor for testing
# Using a simple 2D tensor with batch size 2 and feature dimension 4
input_data = constant([[1.0, 2.0, 3.0, 4.0],
                       [0.5, 1.5, 2.5, 3.5]])

ARGS = {
    "x": input_data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
float2bytes Ran
ran; our contract draft was wrong, not the code
CMU-Perceptual-Computing-Lab/openpose_train/training/generateLmdbFile.py
pointer only (licence: NOASSERTION) · get_code("834cbcb33923be04")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, CMU-Perceptual-Computing-Lab/openpose_train (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_data_paths Ran
ran on a synthesized input
Zero-nnkn/ml-utils/general/dir_utils.py
code served (permissive licence) · get_code("06d66e50cc455cb4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os
from pathlib import Path

# Create temporary directories with test files
temp_dir = tempfile.mkdtemp()
test_subdir = os.path.join(temp_dir, 'subdir')
os.makedirs(test_subdir, exist_ok=True)

# Create some test files with different extensions
Path(os.path.join(temp_dir, 'file1.jpg')).touch()
Path(os.path.join(temp_dir, 'file2.png')).touch()
Path(os.path.join(temp_dir, 'file3.txt')).touch()
Path(os.path.join(test_subdir, 'file4.jpg')).touch()
Path(os.path.join(test_subdir, 'file5.PNG')).touch()

ARGS = {
    'dir': temp_dir,
    'data_formats': ['jpg', 'png'],
    'prefix': '[TEST] '
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_palette Ran
ran on a synthesized input
Zero-nnkn/ml-utils/general/plots.py
code served (permissive licence) · get_code("f9005559e9e55a8a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

ARGS = {
    "num_cls": 8
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
increment_path Ran
ran on a synthesized input
Zero-nnkn/ml-utils/general/file_utils.py
code served (permissive licence) · get_code("ed6d0891a44e6ed1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned PosixPath. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
from pathlib import Path
import os

# Create a temporary directory for testing
temp_dir = tempfile.mkdtemp()

# Define test paths
test_path_1 = os.path.join(temp_dir, "experiment")
test_path_2 = os.path.join(temp_dir, "model.pt")

# Create one of the paths so we can test the increment behavior
Path(test_path_1).mkdir(parents=True, exist_ok=True)

ARGS = {
    "path": test_path_1,
    "exist_ok": False,
    "sep": "_"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PosixPath — a PosixPath output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PosixPath output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_weights Ran
ran on a synthesized input
daniegr/EfficientPose/models/pytorch/EfficientPoseI.py
code served (permissive licence) · get_code("3db00532c993361c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import tempfile
import os

# Create a temporary numpy file with a sample weights dictionary
temp_dir = tempfile.mkdtemp()
weights_dict = {
    'layer1.weight': np.array([[1.0, 2.0], [3.0, 4.0]]),
    'layer1.bias': np.array([0.1, 0.2]),
    'layer2.weight': np.array([[5.0, 6.0, 7.0], [8.0, 9.0, 10.0]])
}

weight_file_path = os.path.join(temp_dir, 'weights.npy')
np.save(weight_file_path, weights_dict)

ARGS = {
    'weight_file': weight_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
swish1 Ran
ran on a synthesized input
daniegr/EfficientPose/utils/helpers.py
code served (permissive licence) · get_code("091dcb41c7f65491")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf
from tensorflow.keras.backend import sigmoid, constant

# Create a small input tensor for testing
# Using a 2x4 tensor as a minimal example
input_data = tf.constant([[1.0, 2.0, 3.0, 4.0],
                          [0.5, 1.5, 2.5, 3.5]], dtype=tf.float32)

ARGS = {
    'x': input_data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
xywh2xyxy Ran
ran on a synthesized input
Zero-nnkn/ml-utils/general/box_utils.py
code served (permissive licence) · get_code("b0b65d41b359206a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function xywh2xyxy converts bounding boxes from center format (x, y, width, height)
# to corner format (x1, y1, x2, y2).
# It accepts either a torch.Tensor or numpy array as input.
# The last dimension must be size 4 (for x, y, w, h values).

# Test with a torch.Tensor
x_tensor = torch.tensor([
    [10.0, 20.0, 4.0, 6.0],
    [30.0, 40.0, 8.0, 10.0]
])

ARGS = {
    "x": x_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
xyxy2xywh Ran
ran on a synthesized input
Zero-nnkn/ml-utils/general/box_utils.py
code served (permissive licence) · get_code("4751d8803935f41a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import torch

torch.manual_seed(0)

# Test with torch.Tensor input
x_torch = torch.tensor([
    [10.0, 20.0, 50.0, 80.0],
    [5.0, 15.0, 35.0, 65.0]
], dtype=torch.float32)

ARGS = {
    "x": x_torch
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
xyxy2xywhn Ran
ran on a synthesized input
Zero-nnkn/ml-utils/general/box_utils.py
code served (permissive licence) · get_code("964295bcda075faf")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create a small tensor with shape (2, 4) representing bounding boxes in xyxy format
# Format: [x1, y1, x2, y2] for each box
x_tensor = torch.tensor([
    [10.0, 20.0, 100.0, 200.0],
    [50.0, 60.0, 150.0, 250.0]
])

ARGS = {
    "x": x_tensor,
    "w": 640,
    "h": 640,
    "clip": False,
    "eps": 0.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
add_keypoints_to_json Not yet run
unverified (harvested, no recorded run)
Zero-nnkn/ml-utils/cv/pose/openpose/openpose.py
code served (permissive licence) · get_code("476a86f50d438198")
How it ran

no invocation recorded.

infer Not yet run
unverified (harvested, no recorded run)
daniegr/EfficientPose/track.py
code served (permissive licence) · get_code("73159ddf6c459bc0")
How it ran

no invocation recorded.

merge_images Not yet run
unverified (harvested, no recorded run)
Zero-nnkn/ml-utils/general/plots.py
code served (permissive licence) · get_code("0d46a5dcabed7526")
How it ran

no invocation recorded.

resize Not yet run
unverified (harvested, no recorded run)
daniegr/EfficientPose/utils/helpers.py
code served (permissive licence) · get_code("3c960223e2a7d66f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 3 later) and 13 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
conv_1x1_bn 31 other papers
3 dated earlier, 2 the same month, 26 later · 2 only as an assembly brick
1703.07402 (2017-03)
Simple Online and Realtime Tracking with a Deep Association Metric
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
1811.08383 (2018-11)
TSM: Temporal Shift Module for Efficient Video Understanding
and 28 more not named here
conv_bn 18 other papers
4 dated earlier, 1 the same month, 13 later · 1 only as an assembly brick
1611.06403 (2016-11)
Deep Outdoor Illumination Estimation
1703.07402 (2017-03)
Simple Online and Realtime Tracking with a Deep Association Metric
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
and 15 more not named here
load_weights 2 other papers
2 later
2305.08192 (2023-05)
Diffusion Models for Imperceptible and Transferable Adversarial Attack
2306.12685 (2023-06)
Rethinking the Backward Propagation for Adversarial Transferability

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

More are linked than shown here.

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Realtime multi-person 2D pose estimation is a key component in enabling machines to have an understanding of people in images and videos. In this work, we present a realtime approach to detect the 2D pose of multiple people in an image. The proposed method uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. This bottom-up system achieves high accuracy and realtime performance, regardless of the number of people in the image. In previous work, PAFs and body part location estimation were refined simultaneously across training stages. We demonstrate that a PAF-only refinement rather than both PAF and body part location refinement results in a substantial increase in both runtime performance and accuracy. We also present the first combined body and foot keypoint detector, based on an internal annotated foot dataset that we have publicly released. We show that the combined detector not only reduces the inference time compared to running them sequentially, but also maintains the accuracy of each component individually. This work has culminated in the release of OpenPose, the first open-source realtime system for multi-person 2D pose detection, including body, foot, hand, and facial keypoints.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1812.08008")
get_code_for_paper("1812.08008")
have("1812.08008")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1812.08008.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1812.08008.svg)](https://syntology.ai/paper/1812.08008)

Connect an agent — have() is free.