SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.07573 · 2018

MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices

arXiv · PDF · Open in the Atlas

Code that ran

33 of 40 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; 7 honoured the contract we drafted, 0 violated it and 16 have no contract verdict; 10 failures of our instrument; 7 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/1804.07573.json · badge: /api/ran/1804.07573.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
TreB1eN/InsightFace_Pytorch community (classifier label)
classifier basis not recorded on the link
13 ran · 2 no recorded run
foamliu/MobileFaceNet community (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
sunil-rival/insightface community (classifier label)
classifier basis not recorded on the link
5 ran · 4 no recorded run
zrui94/insight_mx reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
godofpdog/MobileFaceNet_keras reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
xiaoccer/mobilefacenet_pytorch reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran on a synthesized input
foamliu/MobileFaceNet/facenet_utils.py
code served (permissive licence) · get_code("5636e2d24b43d1a9")
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

torch.manual_seed(0)

# Create small tensors for testing
batch_size = 2
num_classes = 4

# scores: prediction scores, shape (batch_size, num_classes)
# The function calls scores.topk(k, 1, True, True) and ind.eq(targets.view(-1, 1).expand_as(ind))
scores = torch.randn(batch_size, num_classes)

# targets: ground truth class indices, shape (batch_size,)
# The function calls targets.size(0) and targets.view(-1, 1)
targets = torch.tensor([1, 3])

# k: number of top predictions to consider
k = 1

ARGS = {
    "scores": scores,
    "targets": targets,
    "k": k
}
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
adjust_input Ran
ran on a synthesized input
sunil-rival/insightface/rival-src/helper.py
code served (permissive licence) · get_code("603c4089dec3b783")
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 4, dtype family float, shape (1, 3, 4, 3) 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

# Create a small test image array of shape (h, w, c) = (4, 3, 3)
# h=4, w=3, c=3 (RGB channels)
in_data = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)

ARGS = {
    "in_data": in_data
}
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 ndarray, ndim 4, dtype family float, shape (1, 3, 4, 3) — shape (1, 3, 4, 3) 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_accuracy Ran
ran, honoured the contract we drafted
zrui94/insight_mx/src/eval/verification.py
pointer only (licence: NONE) · get_code("f975336b5d5f1a80")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zrui94/insight_mx 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.

calculate_roc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zrui94/insight_mx/src/eval/verification.py
pointer only (licence: NONE) · get_code("db4008738f6c3eae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zrui94/insight_mx 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.

calculate_val Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zrui94/insight_mx/src/eval/verification.py
pointer only (licence: NONE) · get_code("c7c89ea2508beb10")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zrui94/insight_mx 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.

calibrate_box Ran
ran on a synthesized input
TreB1eN/InsightFace_Pytorch/mtcnn_pytorch/src/box_utils.py
code served (permissive licence) · get_code("6b0e6100d2ca104e")
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, 5) 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

# Create sample bounding boxes with shape [n, 5]
# Format: [x1, y1, x2, y2, score]
n = 2
bboxes = np.array([
    [10.0, 20.0, 50.0, 80.0, 0.9],
    [15.0, 25.0, 60.0, 90.0, 0.85]
], dtype=np.float32)

# Create sample offsets with shape [n, 4]
# These are adjustment factors for the bounding box coordinates
offsets = np.array([
    [0.01, 0.02, -0.01, 0.03],
    [0.02, -0.01, 0.01, 0.02]
], dtype=np.float32)

ARGS = {
    "bboxes": bboxes,
    "offsets": offsets
}
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 ndarray, ndim 2, dtype family float, shape (2, 5) — shape (2, 5) 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
checker Ran
ran on a synthesized input
foamliu/MobileFaceNet/create_lfw_test_pair.py
code served (permissive licence) · get_code("c29a1b676bb7bc2e")
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

def checker(lines):
    new_list = []
    for i in range(len(lines) - 1):
        if i % 2 == 0:
            match = int(lines[i].split('/')[0] == lines[i + 1].split('/')[0])
            new_list.append(lines[i] + ' ' + lines[i + 1] + ' ' + str(match))
    return new_list

lines = [
    "path/to/file1.txt",
    "path/to/file2.txt",
    "other/to/file3.txt",
    "other/to/file4.txt",
    "third/to/file5.txt"
]

ARGS = {
    "lines": lines
}
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
convert_to_square Ran
ran on a synthesized input
TreB1eN/InsightFace_Pytorch/mtcnn_pytorch/src/box_utils.py
code served (permissive licence) · get_code("c4e1ca09fcca76fc")
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, 5) 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

# Create a small array of bounding boxes with shape [n, 5]
# n=2 bounding boxes, 5 columns: [x1, y1, x2, y2, confidence]
bboxes = np.array([
    [10.0, 20.0, 50.0, 70.0, 0.9],
    [100.0, 150.0, 200.0, 250.0, 0.8]
], dtype=np.float32)

ARGS = {
    "bboxes": bboxes
}
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 ndarray, ndim 2, dtype family float, shape (2, 5) — shape (2, 5) 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
dummy_loss Ran
ran, honoured the contract we drafted
godofpdog/MobileFaceNet_keras/src/build_model.py
pointer only (licence: NONE) · get_code("505ae2fb5ea0b56b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, godofpdog/MobileFaceNet_keras 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.

file_number Ran
ran on a synthesized input
sunil-rival/insightface/rival-src/embedding_generator.py
code served (permissive licence) · get_code("1928f0825960dbac")
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 str. 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)

ARGS = {
    'number': 42,
    'string_length': 5
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
findNonreflectiveSimilarity Ran
ran, honoured the contract we drafted
TreB1eN/InsightFace_Pytorch/mtcnn_pytorch/src/matlab_cp2tform.py
code served (permissive licence) · get_code("d074710facc3ca20")
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 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 numpy as np

np.random.seed(0)

# Create sample point correspondence data
# uv: source points (2D coordinates)
# xy: target points (2D coordinates)
# We need at least 2 unique points for the transformation to be well-defined
# The function expects M points with 2 coordinates each

uv = np.array([
    [0.0, 0.0],
    [1.0, 0.0],
    [1.0, 1.0],
    [0.0, 1.0]
], dtype=np.float64)

xy = np.array([
    [1.0, 1.0],
    [2.0, 1.5],
    [1.5, 2.5],
    [0.5, 2.0]
], dtype=np.float64)

options = {'K': 2}

ARGS = {
    'uv': uv,
    'xy': xy,
    'options': options
}
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 tuple, ndim 3, dtype family float — 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
getAccuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xiaoccer/mobilefacenet_pytorch/lfw_eval.py
pointer only (licence: NONE) · get_code("52b73c24eeb20194")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoccer/mobilefacenet_pytorch 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.

getThreshold Ran
ran; our contract draft was wrong, not the code
xiaoccer/mobilefacenet_pytorch/lfw_eval.py
pointer only (licence: NONE) · get_code("63f25219eec37d8c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoccer/mobilefacenet_pytorch 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_affine_transform_matrix Ran
ran, honoured the contract we drafted
TreB1eN/InsightFace_Pytorch/mtcnn_pytorch/src/align_trans.py
code served (permissive licence) · get_code("b7f364dbce963974")
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, 3) 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

# Create source points (4 points with x, y coordinates)
src_pts = np.array([
    [10.0, 20.0],
    [30.0, 40.0],
    [50.0, 60.0],
    [70.0, 80.0]
], dtype=np.float32)

# Create destination points (4 points with x, y coordinates)
# These represent where the source points should map to
dst_pts = np.array([
    [15.0, 25.0],
    [35.0, 45.0],
    [55.0, 65.0],
    [75.0, 85.0]
], dtype=np.float32)

ARGS = {
    'src_pts': src_pts,
    'dst_pts': dst_pts
}
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 ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) 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_affine_transform_matrix Ran
ran, honoured the contract we drafted
foamliu/MobileFaceNet/align_faces.py
code served (permissive licence) · get_code("8a6f28d59833cee6")
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, 3) 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

# Create source points: 4 points in 2D space
src_pts = np.array([
    [0.0, 0.0],
    [1.0, 0.0],
    [0.0, 1.0],
    [1.0, 1.0]
], dtype=np.float32)

# Create destination points: 4 points in 2D space (slightly transformed)
dst_pts = np.array([
    [0.5, 0.5],
    [1.5, 0.5],
    [0.5, 1.5],
    [1.5, 1.5]
], dtype=np.float32)

ARGS = {
    'src_pts': src_pts,
    'dst_pts': dst_pts
}
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 ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) 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_block Ran
ran, honoured the contract we drafted
TreB1eN/InsightFace_Pytorch/model.py
code served (permissive licence) · get_code("ad5dbf57f3ea2633")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned list, ndim 2, 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
from collections import namedtuple

torch.manual_seed(0)

# The function get_block takes in_channel, depth, num_units, and stride
# It returns a list of Bottleneck namedtuples

ARGS = {
    'in_channel': 64,
    'depth': 128,
    'num_units': 3,
    'stride': 2
}
Setup block drafted by
a language model, Claude Sonnet 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 list, ndim 2, 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
get_blocks Ran
ran; our contract draft was wrong, not the code
TreB1eN/InsightFace_Pytorch/model.py
pointer only (licence: MIT); the stored copy get_code serves, from VladAndronik/face_swap, is pointer only (licence: NONE) · get_code("ea7941eb1ea8ffb2")
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 VladAndronik/face_swap, 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_config Ran
ran on a synthesized input
TreB1eN/InsightFace_Pytorch/config.py
code served (permissive licence) · get_code("e201c53c13e0fd8b")
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 EasyDict. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
from torch.nn import CrossEntropyLoss
from torchvision import transforms as trans
from pathlib import Path

torch.manual_seed(0)

ARGS = {
    'training': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
easydict, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EasyDict — a EasyDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a EasyDict 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
get_image Ran
ran on a synthesized input
foamliu/MobileFaceNet/custom_eval.py
code served (permissive licence) · get_code("0a6e1a8eb8473974")
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 (4, 3) 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 sample data that matches the structure expected by get_image
samples = [
    {
        'full_path': '/path/to/image1.jpg',
        'face': torch.randn(4, 3)
    },
    {
        'full_path': '/path/to/image2.png',
        'face': torch.randn(4, 3)
    },
    {
        'full_path': '/different/path/target.jpg',
        'face': torch.randn(4, 3)
    }
]

file = 'target.jpg'

ARGS = {
    'samples': samples,
    'file': file
}
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 (4, 3) — shape (4, 3) 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_reference_facial_points Ran
ran on a synthesized input
TreB1eN/InsightFace_Pytorch/mtcnn_pytorch/src/align_trans.py
code served (permissive licence) · get_code("a88ec2b4b2ac122c")
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 (5, 2) 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

ARGS = {
    'output_size': (96, 112),
    'inner_padding_factor': 0.0,
    'outer_padding': (0, 0),
    'default_square': False
}
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 ndarray, ndim 2, dtype family float, shape (5, 2) — shape (5, 2) 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_reference_facial_points Ran
ran on a synthesized input
foamliu/MobileFaceNet/align_faces.py
code served (permissive licence) · get_code("04d256832b55f3fd")
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 (5, 2) 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

ARGS = {
    'output_size': None,
    'inner_padding_factor': 0.0,
    'outer_padding': (0, 0),
    'default_square': False
}
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 ndarray, ndim 2, dtype family float, shape (5, 2) — shape (5, 2) 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
l2_norm Ran
ran; our contract draft was wrong, not the code
TreB1eN/InsightFace_Pytorch/model.py
code served (permissive licence) · get_code("c54fea429589425d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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

torch.manual_seed(0)

input_tensor = torch.randn(2, 4)
axis = 1

ARGS = {
    'input': input_tensor,
    'axis': axis
}
Setup block drafted by
a language model, Claude Sonnet 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 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
lr_scheduler Ran
ran, honoured the contract we drafted
godofpdog/MobileFaceNet_keras/src/build_model.py
pointer only (licence: NONE) · get_code("64d058db63223637")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, godofpdog/MobileFaceNet_keras 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.

nms Ran
ran on a synthesized input
TreB1eN/InsightFace_Pytorch/mtcnn_pytorch/src/box_utils.py
code served (permissive licence) · get_code("522ee6c31c17d845")
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 numpy as np

# Create sample bounding boxes with scores
# Format: [xmin, ymin, xmax, ymax, score]
boxes = np.array([
    [10.0, 20.0, 50.0, 60.0, 0.9],
    [15.0, 25.0, 55.0, 65.0, 0.8],
    [100.0, 100.0, 150.0, 150.0, 0.85],
    [200.0, 200.0, 250.0, 250.0, 0.7],
], dtype=np.float32)

ARGS = {
    'boxes': boxes,
    'overlap_threshold': 0.5,
    'mode': 'union'
}
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 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
nms Ran
ran on a synthesized input
sunil-rival/insightface/rival-src/helper.py
code served (permissive licence) · get_code("04bb405b06233c7b")
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 numpy as np

# Create sample bounding boxes with format [x1, y1, x2, y2, score]
# We'll create 4 boxes with some overlaps
boxes = np.array([
    [10, 10, 50, 50, 0.9],      # box 0, high score
    [15, 15, 55, 55, 0.8],      # box 1, overlaps with box 0
    [100, 100, 150, 150, 0.85], # box 2, no overlap
    [105, 105, 155, 155, 0.7],  # box 3, overlaps with box 2
], dtype='float32')

overlap_threshold = 0.3
mode = 'Union'

ARGS = {
    'boxes': boxes,
    'overlap_threshold': overlap_threshold,
    'mode': mode
}
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 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
parseList Ran
ran; our contract draft was wrong, not the code
xiaoccer/mobilefacenet_pytorch/lfw_eval.py
pointer only (licence: NONE) · get_code("7fda708430211da2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoccer/mobilefacenet_pytorch 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.

parse_arguments Ran
ran; our contract draft was wrong, not the code
godofpdog/MobileFaceNet_keras/train_MobileFaceNet.py
pointer only (licence: NONE) · get_code("a675542da5271225")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, godofpdog/MobileFaceNet_keras 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.

parse_arguments Ran
ran on a synthesized input
sunil-rival/insightface/rival-src/embedding_generator.py
code served (permissive licence) · get_code("e1ae46f172543f30")
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 Namespace. 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 argparse

ARGS = {
    'argv': [
        '--image-size', '112,112',
        '--model', '/path/to/model.pth',
        '--output-dir', '/tmp/output',
        '--image-dir', '/tmp/images',
        '--processors', '4',
        '--batch-size', '32',
        '--ga-model', '/path/to/ga_model.pth',
        '--gpu', '0',
        '--det', '0',
        '--flip', '0',
        '--threshold', '1.24'
    ]
}
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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
range_values_and_batches Ran
ran on a synthesized input
sunil-rival/insightface/rival-src/embedding_generator.py
code served (permissive licence) · get_code("5fe8de82145ecdee")
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 2, 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

torch.manual_seed(0)

class Arguments:
    def __init__(self, batch_size):
        self.batch_size = batch_size

arguments = Arguments(batch_size=3)
total_number_arg = 10

ARGS = {
    "arguments": arguments,
    "total_number_arg": total_number_arg,
}
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 2, 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
read_file Ran
ran on a synthesized input
foamliu/MobileFaceNet/create_lfw_test_pair.py
code served (permissive licence) · get_code("7e9755b0b787bdf3")
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

# Create a temporary file with some test content
temp_dir = tempfile.mkdtemp()
temp_file_path = os.path.join(temp_dir, 'test_file.txt')

with open(temp_file_path, 'w') as f:
    f.write('line one\n')
    f.write('line two\n')
    f.write('\n')
    f.write('line three\n')
    f.write('   \n')
    f.write('line four')

ARGS = {
    'file_path': temp_file_path
}
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
show_bboxes Ran
ran on a synthesized input
TreB1eN/InsightFace_Pytorch/mtcnn_pytorch/src/visualization_utils.py
code served (permissive licence) · get_code("1a075d92bb280328")
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 Image. 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
from PIL import Image

# Create a simple PIL Image (small 100x100 RGB image)
img = Image.new('RGB', (100, 100), color='black')

# Create bounding boxes: shape [n, 5] where n=2
# Each box has [x1, y1, x2, y2, confidence]
bounding_boxes = np.array([
    [10.0, 10.0, 30.0, 30.0, 0.95],
    [40.0, 40.0, 70.0, 70.0, 0.87]
], dtype=np.float32)

# Create facial landmarks: shape [n, 10]
# Each landmark has 5 points with (x, y) coordinates
facial_landmarks = np.array([
    [15.0, 20.0, 25.0, 18.0, 22.0, 15.0, 20.0, 25.0, 18.0, 22.0],
    [45.0, 50.0, 55.0, 48.0, 52.0, 45.0, 50.0, 55.0, 48.0, 52.0]
], dtype=np.float32)

ARGS = {
    'img': img,
    'bounding_boxes': bounding_boxes,
    'facial_landmarks': facial_landmarks
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
tformfwd Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
TreB1eN/InsightFace_Pytorch/mtcnn_pytorch/src/matlab_cp2tform.py
code served (permissive licence) · get_code("b4e2f92e3ce5abc6")
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 (4, 2) 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

# Create a 3x3 affine transformation matrix
trans = np.array([
    [1.0, 0.0, 2.0],
    [0.0, 1.0, 3.0],
    [0.0, 0.0, 1.0]
], dtype=np.float32)

# Create a Kx2 array of coordinates (K=4 points)
uv = np.array([
    [0.0, 0.0],
    [1.0, 1.0],
    [2.0, 3.0],
    [4.0, 5.0]
], dtype=np.float32)

ARGS = {
    "trans": trans,
    "uv": uv
}
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 ndarray, ndim 2, dtype family float, shape (4, 2) — shape (4, 2) 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
tforminv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
TreB1eN/InsightFace_Pytorch/mtcnn_pytorch/src/matlab_cp2tform.py
code served (permissive licence) · get_code("6661cdf22fccc11e")
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 (5, 2) 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

# Create a simple 3x3 affine transformation matrix
# This is a valid transformation matrix for 2D homogeneous coordinates
trans = np.array([
    [1.5, 0.2, 10.0],
    [0.1, 1.3, 5.0],
    [0.0, 0.0, 1.0]
], dtype=np.float64)

# Create sample UV coordinates (Kx2 array)
# K=5 points with (x, y) coordinates
uv = np.array([
    [0.0, 0.0],
    [1.0, 0.0],
    [0.0, 1.0],
    [1.0, 1.0],
    [2.5, 3.7]
], dtype=np.float64)

ARGS = {
    'trans': trans,
    'uv': uv
}
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 ndarray, ndim 2, dtype family float, shape (5, 2) — shape (5, 2) 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_greatest_intra_identity_distance Not yet run
unverified (harvested, no recorded run)
sunil-rival/insightface/rival-src/comparison.py
code served (permissive licence) · get_code("1a81f552c2a2a374")
How it ran

no invocation recorded.

detect_faces Not yet run
unverified (harvested, no recorded run)
TreB1eN/InsightFace_Pytorch/mtcnn_pytorch/src/detector.py
code served (permissive licence) · get_code("15396a0e5161d1a2")
How it ran

no invocation recorded.

embedding_vectors_for_identity Not yet run
unverified (harvested, no recorded run)
sunil-rival/insightface/rival-src/comparison.py
code served (permissive licence) · get_code("77a7c0ac9be8fb3d")
How it ran

no invocation recorded.

find_identity_indexes Not yet run
unverified (harvested, no recorded run)
sunil-rival/insightface/rival-src/comparison.py
code served (permissive licence) · get_code("18cb3da2a93383f5")
How it ran

no invocation recorded.

generate_bbox Not yet run
unverified (harvested, no recorded run)
sunil-rival/insightface/rival-src/helper.py
code served (permissive licence) · get_code("63c1945a6c1bcfa5")
How it ran

no invocation recorded.

run_first_stage Not yet run
unverified (harvested, no recorded run)
TreB1eN/InsightFace_Pytorch/mtcnn_pytorch/src/first_stage.py
code served (permissive licence) · get_code("c2027475131174ef")
How it ran

no invocation recorded.

warp_and_crop_face Not yet run
unverified (harvested, no recorded run)
foamliu/MobileFaceNet/align_faces.py
code served (permissive licence) · get_code("aa98c9a0b502a411")
How it ran

no invocation recorded.

Also present in other papers' code

Of 40 samples lifted from this paper's linked repositories, 40 carry a function identity and 0 do not. Of the 39 distinct functions with an identity, 19 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 18 later) and 20 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
l2_norm 29 other papers
29 later · 2 only as an assembly brick
1903.08527 (2019-03)
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
1907.10830 (2019-07)
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
and 26 more not named here
get_block 27 other papers
27 later
1903.08527 (2019-03)
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
1907.10830 (2019-07)
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
1912.13457 (2019-12)
FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping
and 24 more not named here
get_blocks 16 other papers
16 later
1903.08527 (2019-03)
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
1907.10830 (2019-07)
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
1912.13457 (2019-12)
FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping
and 13 more not named here
calculate_accuracy 12 other papers
6 dated earlier, 6 later
1503.03832 (2015-03)
FaceNet: A Unified Embedding for Face Recognition and Clustering
1607.08221 (2016-07)
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
1703.07737 (2017-03)
In Defense of the Triplet Loss for Person Re-Identification
and 9 more not named here
calculate_roc 5 other papers
3 dated earlier, 2 later
1607.08221 (2016-07)
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
1710.08092 (2017-10)
VGGFace2: A dataset for recognising faces across pose and age
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
and 2 more not named here
calculate_val 4 other papers
3 dated earlier, 1 later
1607.08221 (2016-07)
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
1710.08092 (2017-10)
VGGFace2: A dataset for recognising faces across pose and age
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
and 1 more not named here
get_affine_transform_matrix 4 other papers
4 later
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
2203.11593 (2022-03)
Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition
and 1 more not named here
tformfwd 4 other papers
1 dated earlier, 3 later
1411.7923 (2014-11)
Learning Face Representation from Scratch
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
and 1 more not named here
tforminv 4 other papers
1 dated earlier, 3 later
1411.7923 (2014-11)
Learning Face Representation from Scratch
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
and 1 more not named here
accuracy 3 other papers
3 dated earlier
1508.01211 (2015-08)
Listen, Attend and Spell
1512.01882 (2015-12)
THCHS-30 : A Free Chinese Speech Corpus
1703.03872 (2017-03)
Deep Image Matting
calibrate_box 2 other papers
2 later
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
convert_to_square 2 other papers
2 later
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
findNonreflectiveSimilarity 2 other papers
1 dated earlier, 1 later
1411.7923 (2014-11)
Learning Face Representation from Scratch
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
get_reference_facial_points 2 other papers
2 later
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
nms 2 other papers
2 later
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
show_bboxes 2 other papers
2 later
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
detect_faces 1 other paper
1 later
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
run_first_stage 1 other paper
1 later
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
warp_and_crop_face 1 other paper
1 later
2203.11593 (2022-03)
Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition

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

We present a class of extremely efficient CNN models, MobileFaceNets, which use less than 1 million parameters and are specifically tailored for high-accuracy real-time face verification on mobile and embedded devices. We first make a simple analysis on the weakness of common mobile networks for face verification. The weakness has been well overcome by our specifically designed MobileFaceNets. Under the same experimental conditions, our MobileFaceNets achieve significantly superior accuracy as well as more than 2 times actual speedup over MobileNetV2. After trained by ArcFace loss on the refined MS-Celeb-1M, our single MobileFaceNet of 4.0MB size achieves 99.55% accuracy on LFW and 92.59% TAR@FAR1e-6 on MegaFace, which is even comparable to state-of-the-art big CNN models of hundreds MB size. The fastest one of MobileFaceNets has an actual inference time of 18 milliseconds on a mobile phone. For face verification, MobileFaceNets achieve significantly improved efficiency over previous state-of-the-art mobile CNNs.

For agents

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

get_harvested_code_for_paper("1804.07573")
get_code_for_paper("1804.07573")
have("1804.07573")

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

curl https://syntology.ai/api/ran/1804.07573.json

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

[![Syntology run record](https://syntology.ai/api/ran/1804.07573.svg)](https://syntology.ai/paper/1804.07573)

Connect an agent — have() is free.