SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.07919 · 2019

Deep High-Resolution Representation Learning for Visual Recognition

arXiv · PDF · Open in the Atlas

Code that ran

21 of 34 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, 1 violated it and 12 have no contract verdict; 8 failures of our instrument; 13 no recorded run), measured 2026-11-20; 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/1908.07919.json · badge: /api/ran/1908.07919.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
CSAILVision/semantic-segmentation-pytorch canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
HRNet/HRNet-Facial-Landmark-Detection community (classifier label)
classifier basis: plan_row
7 ran · 5 no recorded run
yuanyuanli85/tf-hrnet community (classifier label)
classifier basis not recorded on the link
5 ran · 2 no recorded run
alililia/ascend_HRNetW48_cls community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
HRNet/HRNet-Image-Classification community (classifier label)
classifier basis not recorded on the link
0 ran · 3 no recorded run
yukichou/PET reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
add_layers Ran
ran on a synthesized input
yuanyuanli85/tf-hrnet/net/utils.py
code served (permissive licence) · get_code("0619db6c90ac8be6")
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 3, 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 tensorflow as tf
import numpy as np
from collections import defaultdict

# Create small TensorFlow tensors for testing
# Each feature map is a tensor that can be added together
tensor1 = tf.constant([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]])
tensor2 = tf.constant([[0.5, 1.0, 1.5, 2.0], [2.5, 3.0, 3.5, 4.0]])
tensor3 = tf.constant([[0.1, 0.2, 0.3, 0.4], [0.5, 0.6, 0.7, 0.8]])

# Build dictionaries mapping output indices to lists of feature tensors
origfeatures = defaultdict(list)
origfeatures[0] = [tensor1]
origfeatures[1] = [tensor2]
origfeatures[2] = [tensor3]

dwfeatures = defaultdict(list)
dwfeatures[0] = [tensor2]
dwfeatures[2] = [tensor1]

upfeatures = defaultdict(list)
upfeatures[0] = [tensor3]
upfeatures[1] = [tensor1]

nums_output = 3

ARGS = {
    "origfeatures": origfeatures,
    "dwfeatrues": dwfeatures,
    "upfeatures": upfeatures,
    "nums_output": nums_output
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 3, 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
as_variable Ran
ran on a synthesized input
CSAILVision/semantic-segmentation-pytorch/mit_semseg/lib/utils/th.py
code served (permissive licence) · get_code("10bb6a2d70d61ca6")
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 collections
from torch.autograd import Variable

torch.manual_seed(0)

# Test with a simple tensor
tensor_obj = torch.randn(2, 4)

# Test with a sequence (list)
sequence_obj = [torch.randn(2, 4), torch.randn(3, 5)]

# Test with a mapping (dict)
mapping_obj = {
    'a': torch.randn(2, 4),
    'b': torch.randn(3, 5)
}

# Test with nested structure
nested_obj = {
    'tensors': [torch.randn(2, 4), torch.randn(1, 3)],
    'single': torch.randn(4, 2)
}

# Create ARGS dict mapping the parameter 'obj' to each test case
ARGS = {
    'obj': tensor_obj
}
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 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
calculate_fan_in_and_fan_out Ran
ran on a synthesized input
alililia/ascend_HRNetW48_cls/src/utils.py
code served (permissive licence) · get_code("74bebe7a4353815b")
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 tuple, 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
import numpy as np

torch.manual_seed(0)

# Test case 1: 2D tensor (linear layer weight shape)
shape_2d = (5, 3)

# Test case 2: 4D tensor (conv2d weight shape: out_channels, in_channels, height, width)
shape_4d = (8, 4, 3, 3)

# Using the 2D case as the primary test
ARGS = {
    "shape": shape_2d
}
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 tuple, ndim 1, dtype family int — a tuple 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
compute_nme Ran
ran on a synthesized input
HRNet/HRNet-Facial-Landmark-Detection/lib/core/evaluation.py
pointer only (licence: MIT) · get_code("6de0c395f2ed480f")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Facial-Landmark-Detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
HRNet/HRNet-Facial-Landmark-Detection/lib/models/hrnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Facial-Landmark-Detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

create_downsample_fn_matrix Ran
ran on a synthesized input
yuanyuanli85/tf-hrnet/net/utils.py
code served (permissive licence) · get_code("f6318bc574966adf")
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 torch
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - num_branches: integer, used in range()
# - inputs: indexed with i (range 0 to num_branches-1), values stored in dict
# - num_output_branches: integer, used in range()
# - output_channels: indexed with j (range 0 to num_output_branches-1), values stored in dict

# inputs should be a list/indexable with num_branches elements
# output_channels should be a list/indexable with num_output_branches elements

num_branches = 3
num_output_branches = 4

# Create inputs - list of 3 distinct tensor identifiers (could be strings, ints, or tensors)
inputs = ["input_0", "input_1", "input_2"]

# Create output_channels - list of 4 distinct channel counts
output_channels = [16, 32, 64, 128]

ARGS = {
    "num_branches": num_branches,
    "inputs": inputs,
    "num_output_branches": num_output_branches,
    "output_channels": output_channels
}
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 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
create_logger Ran
ran on a synthesized input
HRNet/HRNet-Facial-Landmark-Detection/lib/utils/utils.py
pointer only (licence: MIT) · get_code("d40435a99888f5a8")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Facial-Landmark-Detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

create_upsample_fn_matrix Ran
ran on a synthesized input
yuanyuanli85/tf-hrnet/net/utils.py
code served (permissive licence) · get_code("0944678dd9feace7")
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 torch

torch.manual_seed(0)

num_branches = 3
num_output_branches = 2

# inputs: list of tensors, one per branch
inputs = [
    torch.randn(2, 4),  # branch 0
    torch.randn(2, 5),  # branch 1
    torch.randn(2, 6),  # branch 2
]

# output_channels: list of channel counts, one per output branch
output_channels = [8, 16]

ARGS = {
    'num_branches': num_branches,
    'inputs': inputs,
    'num_output_branches': num_output_branches,
    'output_channels': output_channels,
}
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 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
find_recursive Ran
ran; our contract draft was wrong, not the code
CSAILVision/semantic-segmentation-pytorch/mit_semseg/utils.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from YuxiaoWang-AI/P3HOT, is pointer only (licence: NONE) · get_code("6890565633b480b8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from YuxiaoWang-AI/P3HOT, 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_3rd_point Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
HRNet/HRNet-Facial-Landmark-Detection/lib/utils/transforms.py
pointer only (licence: MIT); the stored copy get_code serves, from kmax2001/EvSharp2Blur, is pointer only (licence: NONE) · get_code("9084d28f30c5495b")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Facial-Landmark-Detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

get_dir Ran
ran, violated the contract we drafted
HRNet/HRNet-Facial-Landmark-Detection/lib/utils/transforms.py
pointer only (licence: MIT) · get_code("5d546e1ecbee1866")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Facial-Landmark-Detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

get_global_step_from_ckpt Ran
ran on a synthesized input
yuanyuanli85/tf-hrnet/trainer/utils.py
code served (permissive licence) · get_code("0db1a7c39ef342bb")
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 int, ndim 0, dtype family int, 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 re

def get_global_step_from_ckpt(ckptpath):
    step = re.findall('model.ckpt-(\\d+)', ckptpath)
    return int(step[0])

# The function takes a checkpoint path string and extracts a step number
# It uses regex to find 'model.ckpt-<digits>' pattern
ckptpath = "path/to/model.ckpt-42500"

ARGS = {
    "ckptpath": ckptpath
}
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 int, ndim 0, dtype family int, 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
get_linear_lr Ran
ran on a synthesized input
alililia/ascend_HRNetW48_cls/src/utils.py
code served (permissive licence) · get_code("da92159bb9c47108")
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 torch
import numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - base_lr: float, base learning rate
# - total_epoch: int, total number of epochs
# - spe: int, steps per epoch
# - lr_init: float, initial learning rate for warmup
# - lr_end: float, final learning rate after decay
# - warmup_epoch: int, number of warmup epochs (default 0)
# The function computes a list of learning rates for each step
# All parameters are numeric types (int/float)

ARGS = {
    "base_lr": 0.1,
    "total_epoch": 10,
    "spe": 100,
    "lr_init": 0.0,
    "lr_end": 0.01,
    "warmup_epoch": 2,
}
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 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_optimizer Ran
ran on a synthesized input
HRNet/HRNet-Facial-Landmark-Detection/lib/utils/utils.py
pointer only (licence: MIT) · get_code("f22f739c65e1ada2")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Facial-Landmark-Detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

get_preds Ran
ran; our contract draft was wrong, not the code
HRNet/HRNet-Facial-Landmark-Detection/lib/core/evaluation.py
pointer only (licence: MIT) · get_code("8edd86bd9a43d59e")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Facial-Landmark-Detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

he_normal_fanout Ran
ran on a synthesized input
yuanyuanli85/tf-hrnet/net/model.py
code served (permissive licence) · get_code("963be56113879485")
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 VarianceScaling. 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 tensorflow as tf
from tensorflow.python.ops.init_ops import VarianceScaling

# The function he_normal_fanout takes only one parameter: seed
# It can be None or an integer seed value for reproducibility

ARGS = {
    'seed': None
}
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 VarianceScaling — a VarianceScaling output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a VarianceScaling 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
imresize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
CSAILVision/semantic-segmentation-pytorch/mit_semseg/dataset.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from YuxiaoWang-AI/P3HOT, is pointer only (licence: NONE) · get_code("e23968c493407287")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from YuxiaoWang-AI/P3HOT, 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.

load_url Ran
ran; our contract draft was wrong, not the code
CSAILVision/semantic-segmentation-pytorch/mit_semseg/models/utils.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from YuxiaoWang-AI/P3HOT, is pointer only (licence: NONE) · get_code("d087e320591e6ba7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from YuxiaoWang-AI/P3HOT, 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.

mark_volatile Ran
ran on a synthesized input
CSAILVision/semantic-segmentation-pytorch/mit_semseg/lib/utils/th.py
code served (permissive licence) · get_code("32f45cf75891bd16")
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
from torch.autograd import Variable
import collections

torch.manual_seed(0)

# Test case 1: Tensor input
tensor_input = torch.randn(2, 4)

# Test case 2: Variable input
variable_input = Variable(torch.randn(2, 4))

# Test case 3: Dict/Mapping input
dict_input = {
    'tensor': torch.randn(2, 4),
    'variable': Variable(torch.randn(2, 4)),
    'nested': {
        'value': torch.randn(2, 4)
    }
}

# Test case 4: List/Sequence input
list_input = [
    torch.randn(2, 4),
    Variable(torch.randn(2, 4)),
    {'key': torch.randn(2, 4)}
]

# Test case 5: Scalar/other type
scalar_input = 42

# The function takes one parameter: obj
# We'll test with a tensor as the primary case
ARGS = {
    'obj': torch.randn(2, 4)
}
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 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
setup_logger Ran
ran; our contract draft was wrong, not the code
CSAILVision/semantic-segmentation-pytorch/mit_semseg/utils.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from YuxiaoWang-AI/P3HOT, is pointer only (licence: NONE) · get_code("b50608a902a34b99")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from YuxiaoWang-AI/P3HOT, 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.

unique Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
CSAILVision/semantic-segmentation-pytorch/mit_semseg/utils.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from YuxiaoWang-AI/P3HOT, is pointer only (licence: NONE) · get_code("5feabe579b35978a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from YuxiaoWang-AI/P3HOT, 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.

accuracy Not yet run
unverified (harvested, no recorded run)
HRNet/HRNet-Image-Classification/lib/core/evaluate.py
pointer only (licence: MIT) · get_code("390a8904d4707b9d")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Image-Classification, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

as_numpy Not yet run
unverified (harvested, no recorded run)
CSAILVision/semantic-segmentation-pytorch/mit_semseg/lib/utils/th.py
code served (permissive licence) · get_code("c08e7121f699a983")
How it ran

no invocation recorded.

decode_preds Not yet run
unverified (harvested, no recorded run)
HRNet/HRNet-Facial-Landmark-Detection/lib/core/evaluation.py
pointer only (licence: MIT) · get_code("e05de20d97ad0edc")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Facial-Landmark-Detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

fliplr_joints Not yet run
unverified (harvested, no recorded run)
HRNet/HRNet-Facial-Landmark-Detection/lib/utils/transforms.py
pointer only (licence: MIT) · get_code("c2d2699886a4a219")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Facial-Landmark-Detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

get_cls_net Not yet run
unverified (harvested, no recorded run)
yukichou/PET/lib/models/cls_hrnet.py
code served (permissive licence) · get_code("ab06e83afc0afd03")
How it ran

no invocation recorded.

get_cls_net Not yet run
unverified (harvested, no recorded run)
HRNet/HRNet-Image-Classification/lib/models/cls_hrnet.py
pointer only (licence: MIT) · get_code("2536e03f883a249b")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Image-Classification, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

get_face_alignment_net Not yet run
unverified (harvested, no recorded run)
HRNet/HRNet-Facial-Landmark-Detection/lib/models/hrnet.py
pointer only (licence: MIT) · get_code("9011a68305d287a7")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Facial-Landmark-Detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

get_model_summary Not yet run
unverified (harvested, no recorded run)
HRNet/HRNet-Image-Classification/lib/utils/modelsummary.py
pointer only (licence: MIT) · get_code("c6f52ade1e2640aa")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Image-Classification, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

get_pose_net Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from wsjzha/deep-high-resolution-net.pytorch
pointer only · get_code("2534c81208f21998")
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. No invocation recorded.

inference Not yet run
unverified (harvested, no recorded run)
HRNet/HRNet-Facial-Landmark-Detection/lib/core/function.py
pointer only (licence: MIT) · get_code("294428702976ffdf")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Facial-Landmark-Detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

parse_example_proto Not yet run
unverified (harvested, no recorded run)
yuanyuanli85/tf-hrnet/datasets/ilsvrc12_dataset.py
code served (permissive licence) · get_code("31327aeaa8ee6db0")
How it ran

no invocation recorded.

preprocess_image Not yet run
unverified (harvested, no recorded run)
yuanyuanli85/tf-hrnet/utils/imagenet_preprocessing.py
code served (permissive licence) · get_code("c209215a8aa50633")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
HRNet/HRNet-Facial-Landmark-Detection/lib/core/function.py
pointer only (licence: MIT) · get_code("72f5b582b4e52e05")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, HRNet/HRNet-Facial-Landmark-Detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

Also present in other papers' code

Of 34 samples lifted from this paper's linked repositories, 34 carry a function identity and 0 do not. Of the 33 distinct functions with an identity, 17 are also present in other papers whose code we hold (15 with at least one paper dated earlier, 4 the same month, 13 later) and 16 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
conv3x3 686 other papers
143 dated earlier, 10 the same month, 533 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
accuracy 80 other papers
24 dated earlier, 1 the same month, 55 later
1307.0414 (2013-07)
Challenges in Representation Learning: A report on three machine learning contests
1412.6553 (2014-12)
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
1503.02531 (2015-03)
Distilling the Knowledge in a Neural Network
and 77 more not named here
get_dir 7 other papers
1 dated earlier, 6 later · 1 only as an assembly brick
1906.07155 (2019-06)
MMDetection: Open MMLab Detection Toolbox and Benchmark
2105.04154 (2021-05)
Unsupervised Human Pose Estimation through Transforming Shape Templates
2107.13774 (2021-07)
Geometry Uncertainty Projection Network for Monocular 3D Object Detection
and 4 more not named here
imresize 6 other papers
3 dated earlier, 3 later
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1810.04020 (2018-10)
A Comprehensive Survey of Deep Learning for Image Captioning
1904.04514 (2019-04)
High-Resolution Representations for Labeling Pixels and Regions
and 3 more not named here
unique 6 other papers
3 dated earlier, 3 later
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1807.11590 (2018-07)
Acquisition of Localization Confidence for Accurate Object Detection
1904.04514 (2019-04)
High-Resolution Representations for Labeling Pixels and Regions
and 3 more not named here
get_3rd_point 5 other papers
1 dated earlier, 4 later
1906.07155 (2019-06)
MMDetection: Open MMLab Detection Toolbox and Benchmark
2105.04154 (2021-05)
Unsupervised Human Pose Estimation through Transforming Shape Templates
2403.08019 (2024-03)
MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation
and 2 more not named here
get_pose_net 5 other papers
2 dated earlier, 1 the same month, 2 later
1902.09212 (2019-02)
Deep High-Resolution Representation Learning for Human Pose Estimation
1904.04514 (2019-04)
High-Resolution Representations for Labeling Pixels and Regions
1908.10357 (2019-08)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
and 2 more not named here
load_url 4 other papers
3 dated earlier, 1 later
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1807.11590 (2018-07)
Acquisition of Localization Confidence for Accurate Object Detection
1904.04514 (2019-04)
High-Resolution Representations for Labeling Pixels and Regions
and 1 more not named here
find_recursive 3 other papers
2 dated earlier, 1 later
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1904.04514 (2019-04)
High-Resolution Representations for Labeling Pixels and Regions
2507.01630 (2025-07)
Prompt Guidance and Human Proximal Perception for HOT Prediction with Regional Joint Loss
setup_logger 3 other papers
2 dated earlier, 1 later
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1904.04514 (2019-04)
High-Resolution Representations for Labeling Pixels and Regions
2507.01630 (2025-07)
Prompt Guidance and Human Proximal Perception for HOT Prediction with Regional Joint Loss
as_numpy 2 other papers
2 dated earlier
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1904.04514 (2019-04)
High-Resolution Representations for Labeling Pixels and Regions
as_variable 2 other papers
2 dated earlier
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1904.04514 (2019-04)
High-Resolution Representations for Labeling Pixels and Regions
get_face_alignment_net 2 other papers
1 the same month, 1 later
1908.05932 (2019-08)
FSGAN: Subject Agnostic Face Swapping and Reenactment
2212.01927 (2022-12)
Label Encoding for Regression Networks
mark_volatile 2 other papers
2 dated earlier
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1904.04514 (2019-04)
High-Resolution Representations for Labeling Pixels and Regions
preprocess_image 2 other papers
1 dated earlier, 1 later
1904.01569 (2019-04)
Exploring Randomly Wired Neural Networks for Image Recognition
aaai_16474 (2021 (year only))
Optimizing Information Theory Based Bitwise Bottlenecks for Efficient Mixed-Precision Activation Quantization
calculate_fan_in_and_fan_out 1 other paper
1 dated earlier
1506.01497 (2015-06)
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
get_preds 1 other paper
1 later
1912.08265 (2019-12)
Learning from Synthetic Animals

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 2026-11-20.

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

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions \emph{in series} (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams \emph{in parallel}; (ii) Repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at~{\url{https://github.com/HRNet}}.

For agents

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

get_harvested_code_for_paper("1908.07919")
get_code_for_paper("1908.07919")
have("1908.07919")

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

curl https://syntology.ai/api/ran/1908.07919.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.07919.svg)](https://syntology.ai/paper/1908.07919)

Connect an agent — have() is free.