SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.08265 · 2019

Learning from Synthetic Animals

arXiv · PDF · Open in the Atlas

Code that ran

7 of 15 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; 1 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 1 failure of our instrument; 8 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/1912.08265.json · badge: /api/ran/1912.08265.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
chaneyddtt/UDA-Animal-Pose community (classifier label)
classifier basis not recorded on the link
7 ran · 8 no recorded run
FunctionStatusWhere it lives
adjust_learning_rate Ran
ran on a synthesized input
chaneyddtt/UDA-Animal-Pose/pose/utils/misc.py
code served (permissive licence) · get_code("c909dbba49acbe18")
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 float, ndim 0, dtype family float, shape () 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 torch.nn as nn
from torch.optim import SGD

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 2)

# Create an optimizer
optimizer = SGD(model.parameters(), lr=0.1)

# Define arguments for adjust_learning_rate
ARGS = {
    'optimizer': optimizer,
    'epoch': 5,
    'lr': 0.1,
    'schedule': [5, 10, 15],
    'gamma': 0.1
}
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 float, ndim 0, dtype family float, shape () — shape () 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
isdir Ran
ran on a synthesized input
chaneyddtt/UDA-Animal-Pose/pose/utils/osutils.py
code served (permissive licence) · get_code("0acd5efef92b5edf")
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 bool, ndim 0, dtype family float, shape () 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 os
import tempfile

# Create a temporary directory to test with
temp_dir = tempfile.mkdtemp()

ARGS = {
    "dirname": temp_dir
}
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 bool, ndim 0, dtype family float, shape () — shape () 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
isfile Ran
ran on a synthesized input
chaneyddtt/UDA-Animal-Pose/pose/utils/osutils.py
code served (permissive licence) · get_code("92a1e3f86eb91801")
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 bool, ndim 0, dtype family float, shape () 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 os
import tempfile

# Create a temporary file for testing
with tempfile.NamedTemporaryFile(delete=False) as tmp:
    tmp_path = tmp.name

ARGS = {
    "fname": tmp_path
}

# Clean up after defining ARGS
try:
    os.unlink(tmp_path)
except:
    pass
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 bool, ndim 0, dtype family float, shape () — shape () 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
plot_overlap Ran
ran; our contract draft was wrong, not the code
chaneyddtt/UDA-Animal-Pose/pose/utils/logger.py
code served (permissive licence) · get_code("921113cf2a16c965")
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 numpy as np

class MockLogger:
    def __init__(self):
        self.title = "test_plot"
        self.names = ["loss", "accuracy", "f1_score"]
        self.numbers = {
            "loss": [0.5, 0.4, 0.3, 0.2],
            "accuracy": [0.6, 0.7, 0.8, 0.9],
            "f1_score": [0.55, 0.65, 0.75, 0.85]
        }

logger = MockLogger()

ARGS = {
    "logger": logger,
    "names": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — 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
symmetric_mse_loss Ran
ran on a synthesized input
chaneyddtt/UDA-Animal-Pose/pose/losses/jointsmseloss.py
code served (permissive licence) · get_code("46dd6446e6572188")
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 0, dtype family float, shape () 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 torch.nn as nn

torch.manual_seed(0)

# The function expects two tensors of the same size
# It computes MSE loss between them and returns 0.5 * loss
# Both tensors need to support .size() method and arithmetic operations

input1 = torch.randn(2, 4, requires_grad=True)
input2 = torch.randn(2, 4, requires_grad=True)

ARGS = {
    "input1": input1,
    "input2": input2,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
to_numpy Ran
ran on a synthesized input
chaneyddtt/UDA-Animal-Pose/pose/utils/misc.py
code served (permissive licence) · get_code("f3049ed43335c350")
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 ndarray, 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)

# Test case 1: PyTorch tensor (the main use case)
tensor_arg = torch.randn(2, 4)

# Test case 2: NumPy array (should pass through)
numpy_arg = np.array([[1, 2, 3], [4, 5, 6]])

# Create ARGS dict with both parameter values
# We'll test with the tensor first, as that's the primary use case
ARGS = {
    'tensor': tensor_arg
}
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 ndarray, 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
to_torch Ran
ran, honoured the contract we drafted
chaneyddtt/UDA-Animal-Pose/pose/utils/misc.py
pointer only (licence: MIT); the stored copy get_code serves, from liu-xb/GCMT, is pointer only (licence: NONE) · get_code("7aac4c51e0ceee97")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from liu-xb/GCMT, and GitHub detected no licence in that repository when it was checked. 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_preds Not yet run
unverified (harvested, no recorded run)
chaneyddtt/UDA-Animal-Pose/pose/utils/evaluation.py
code served (permissive licence) · get_code("b095d4004cfba4fb")
How it ran

no invocation recorded.

get_preds_all Not yet run
unverified (harvested, no recorded run)
chaneyddtt/UDA-Animal-Pose/pose/utils/evaluation.py
code served (permissive licence) · get_code("6a15f00353702e4c")
How it ran

no invocation recorded.

get_warpmat Not yet run
unverified (harvested, no recorded run)
chaneyddtt/UDA-Animal-Pose/pose/datasets/real_animal_crop_all.py
code served (permissive licence) · get_code("cecb866afc37e96a")
How it ran

no invocation recorded.

im_to_numpy Not yet run
unverified (harvested, no recorded run)
chaneyddtt/UDA-Animal-Pose/pose/utils/imutils.py
code served (permissive licence) · get_code("0f501bcb9a1fda50")
How it ran

no invocation recorded.

im_to_torch Not yet run
unverified (harvested, no recorded run)
chaneyddtt/UDA-Animal-Pose/pose/utils/imutils.py
code served (permissive licence) · get_code("c98eeba8cbddf187")
How it ran

no invocation recorded.

join Not yet run
unverified (harvested, no recorded run)
chaneyddtt/UDA-Animal-Pose/pose/utils/osutils.py
code served (permissive licence) · get_code("3ad7d84a2bb4a334")
How it ran

no invocation recorded.

load_image_ori Not yet run
unverified (harvested, no recorded run)
chaneyddtt/UDA-Animal-Pose/pose/utils/imutils.py
code served (permissive licence) · get_code("a09aa9316ab8bff6")
How it ran

no invocation recorded.

mpii_calc_dists Not yet run
unverified (harvested, no recorded run)
chaneyddtt/UDA-Animal-Pose/pose/utils/evaluation.py
code served (permissive licence) · get_code("6f69c035a4b866ae")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 6 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 5 later) and 9 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
plot_overlap 31 other papers
13 dated earlier, 18 later
1612.06321 (2016-12)
Large-Scale Image Retrieval with Attentive Deep Local Features
1805.07925 (2018-05)
Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks
1806.04606 (2018-06)
Knowledge Distillation by On-the-Fly Native Ensemble
and 28 more not named here
to_torch 9 other papers
9 later · 3 only as an assembly brick
2003.02501 (2020-03)
Detecting Attended Visual Targets in Video
2007.09919 (2020-07)
Robust Tracking against Adversarial Attacks
2103.11658 (2021-03)
Intra-Inter Camera Similarity for Unsupervised Person Re-Identification
and 6 more not named here
im_to_numpy 3 other papers
3 later
2007.09919 (2020-07)
Robust Tracking against Adversarial Attacks
136670327 (2022 (year only))
Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization
2308.09951 (2023-08)
Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos
adjust_learning_rate 1 other paper
1 later
2108.08478 (2021-08)
Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction
get_preds 1 other paper
1 dated earlier
1908.07919 (2019-08)
Deep High-Resolution Representation Learning for Visual Recognition
im_to_torch 1 other paper
1 later
136670327 (2022 (year only))
Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization

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

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

Abstract

Despite great success in human parsing, progress for parsing other deformable articulated objects, like animals, is still limited by the lack of labeled data. In this paper, we use synthetic images and ground truth generated from CAD animal models to address this challenge. To bridge the domain gap between real and synthetic images, we propose a novel consistency-constrained semi-supervised learning method (CC-SSL). Our method leverages both spatial and temporal consistencies, to bootstrap weak models trained on synthetic data with unlabeled real images. We demonstrate the effectiveness of our method on highly deformable animals, such as horses and tigers. Without using any real image label, our method allows for accurate keypoint prediction on real images. Moreover, we quantitatively show that models using synthetic data achieve better generalization performance than models trained on real images across different domains in the Visual Domain Adaptation Challenge dataset. Our synthetic dataset contains 10+ animals with diverse poses and rich ground truth, which enables us to use the multi-task learning strategy to further boost models' performance.

For agents

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

get_harvested_code_for_paper("1912.08265")
get_code_for_paper("1912.08265")
have("1912.08265")

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

curl https://syntology.ai/api/ran/1912.08265.json

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

[![Syntology run record](https://syntology.ai/api/ran/1912.08265.svg)](https://syntology.ai/paper/1912.08265)

Connect an agent — have() is free.