SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1703.10593 · 2017

Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

arXiv · PDF · Open in the Atlas

Code that ran

14 of 31 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 11 failures of our instrument; 17 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/1703.10593.json · badge: /api/ran/1703.10593.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
ranery/Bayesian-CycleGAN community (classifier label)
classifier basis not recorded on the link
5 ran · 4 no recorded run
nahliabdelwahed/Face-Image-Deblurring community (classifier label)
classifier basis not recorded on the link
3 ran · 4 no recorded run
NiucunCode/Deep-Learning-proj2 reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
JL321/CycleGAN reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
leehomyc/cyclegan-1 reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
racinmat/anime-style-transfer reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
jackaduma/CycleGAN-VC2 reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
NeuralVFX/lighting-swap-cyclegan extension (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
yex666/cyclegan-in-mindspore community (classifier label)
classifier basis not recorded on the link
0 ran · 4 no recorded run
vanhuyz/CycleGAN-TensorFlow community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
tmabraham/UPIT reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
karl-hajjar/Generative-Adversarial-Networks reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
Adi-iitd/AI-Art reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
analyze_div Ran
ran; our contract draft was wrong, not the code
ranery/Bayesian-CycleGAN/evaluation/div.py
code served (permissive licence) · get_code("5558a586ed0f084e")
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. 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

# Set random seed for reproducibility
np.random.seed(0)

# Create small synthetic datasets
# X_real: real data samples (batch_size=20, features=4)
X_real = np.random.randn(20, 4)

# X_sample: generated/sampled data (batch_size=20, features=4)
X_sample = np.random.randn(20, 4) + 0.5

ARGS = {
    "X_real": X_real,
    "X_sample": X_sample,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
batch_convert2int Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
nahliabdelwahed/Face-Image-Deblurring/CycleGAN/CycleGAN_Code/utils.py
code served (permissive licence) · get_code("cf8ebd33964671ae")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 4, dtype family int, shape (2, 4, 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 tensorflow as tf
import numpy as np

# Create a small 4D float tensor in the range [-1., 1.]
# Shape: (batch_size=2, image_size=4, image_size=3, depth=3)
batch_size = 2
image_size = 4
depth = 3
images = tf.constant(
    np.random.uniform(-1.0, 1.0, size=(batch_size, image_size, image_size, depth)),
    dtype=tf.float32
)

ARGS = {
    "images": images
}
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 EagerTensor, ndim 4, dtype family int, shape (2, 4, 4, 3) — shape (2, 4, 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
batch_shape Ran
ran; our contract draft was wrong, not the code
JL321/CycleGAN/cycleGAN.py
pointer only (licence: NONE) · get_code("52ab9586152ff082")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JL321/CycleGAN 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_frechet_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ranery/Bayesian-CycleGAN/evaluation/fid.py
code served (permissive licence) · get_code("846d824d45774de9")
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 float64, ndim 0, 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
from scipy import linalg
import warnings

# Set random seed for reproducibility
np.random.seed(0)

# Create small sample data for Frechet Distance calculation
# The function expects mean vectors and covariance matrices from activation distributions

# Dimension of activation space (e.g., from Inception network pool_3 layer)
activation_dim = 4

# Number of samples for computing statistics
num_samples = 2

# Generate sample activations for two distributions
activations1 = np.random.randn(num_samples, activation_dim)
activations2 = np.random.randn(num_samples, activation_dim)

# Compute mean vectors
mu1 = np.mean(activations1, axis=0)  # shape: (4,)
mu2 = np.mean(activations2, axis=0)  # shape: (4,)

# Compute covariance matrices
sigma1 = np.cov(activations1.T)  # shape: (4, 4)
sigma2 = np.cov(activations2.T)  # shape: (4, 4)

# Ensure covariance matrices are positive definite by adding small regularization
epsilon = 1e-6
sigma1 = sigma1 + epsilon * np.eye(activation_dim)
sigma2 = sigma2 + epsilon * np.eye(activation_dim)

ARGS = {
    'mu1': mu1,
    'sigma1': sigma1,
    'mu2': mu2,
    'sigma2': sigma2,
    'eps': 1e-06
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
convert2float Ran
ran, violated the contract we drafted
nahliabdelwahed/Face-Image-Deblurring/CycleGAN/CycleGAN_Code/utils.py
code served (permissive licence) · get_code("8784e48570a63b64")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 3, dtype family float, shape (2, 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 tensorflow as tf
import numpy as np

# Create a small test image tensor with integer values in [0, 255]
# Using shape (2, 4, 3) for batch_size=2, height=4, width=3, channels=3
image_data = np.array([
    [[255, 128, 0], [100, 50, 200], [10, 255, 100], [200, 50, 10]],
    [[0, 127, 255], [200, 100, 50], [128, 64, 32], [255, 200, 150]]
], dtype=np.uint8)

image = tf.constant(image_data)

ARGS = {
    "image": image
}
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 EagerTensor, ndim 3, dtype family float, shape (2, 4, 3) — shape (2, 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
convert2int Ran
ran, violated the contract we drafted
nahliabdelwahed/Face-Image-Deblurring/CycleGAN/CycleGAN_Code/utils.py
code served (permissive licence) · get_code("c176df774e2aaf48")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 3, dtype family int, shape (2, 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 tensorflow as tf
import numpy as np

# Create a small float tensor in the range [-1., 1.]
# Shape: (2, 4, 3) - batch of 2, spatial dims 4x3, 3 channels (RGB)
image_data = np.random.uniform(-1.0, 1.0, size=(2, 4, 3)).astype(np.float32)
image = tf.constant(image_data)

ARGS = {
    "image": image
}
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 EagerTensor, ndim 3, dtype family int, shape (2, 4, 3) — shape (2, 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
create_list Ran
ran; our contract draft was wrong, not the code
leehomyc/cyclegan-1/create_cyclegan_dataset.py
code served (permissive licence) · get_code("85f23642dbfe3b9c")
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 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 os
import tempfile
import shutil

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

# Create some test files with different suffixes
test_files = [
    'image1.jpg',
    'image2.jpg',
    'document.txt',
    'photo.png',
    'picture3.jpg'
]

for filename in test_files:
    filepath = os.path.join(temp_dir, filename)
    with open(filepath, 'w') as f:
        f.write('test')

ARGS = {
    'foldername': temp_dir,
    'fulldir': True,
    'suffix': '.jpg'
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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
criterion_cls Ran
ran; our contract draft was wrong, not the code
NiucunCode/Deep-Learning-proj2/stargan/stargan.py
pointer only (licence: NONE) · get_code("b2c2f67d29748a94")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NiucunCode/Deep-Learning-proj2 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.

define_D Ran
ran; our contract draft was wrong, not the code
ranery/Bayesian-CycleGAN/models/networks.py
code served (permissive licence) · get_code("514b952ec6180601")
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 MultiscaleDiscriminator. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import functools
import numpy as np

torch.manual_seed(0)

ARGS = {
    'input_nc': 3,
    'ndf': 64,
    'n_layers_D': 3,
    'norm': 'instance',
    'use_sigmoid': False,
    'num_D': 3
}
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 MultiscaleDiscriminator — a MultiscaleDiscriminator output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MultiscaleDiscriminator 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_base_name Ran
ran; our contract draft was wrong, not the code
racinmat/anime-style-transfer/code/mod-cycle-gan/transform.py
pointer only (licence: NONE) · get_code("2154eb6f5c5d24f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, racinmat/anime-style-transfer 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_norm_layer Ran
ran; our contract draft was wrong, not the code
ranery/Bayesian-CycleGAN/models/networks.py
code served (permissive licence) · get_code("ad8798affe75a564")
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 partial. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import functools

torch.manual_seed(0)

ARGS = {
    'norm_type': 'instance'
}
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 partial — a partial output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a partial 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
im2index Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ranery/Bayesian-CycleGAN/datasets/color2index.py
code served (permissive licence) · get_code("b8753062e482c978")
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 3, dtype family int, shape (2, 3, 1) 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 RGB image with colors that exist in the color2index dictionary
# Image shape: (height=2, width=3, channels=3)
im = np.zeros((2, 3, 3), dtype=np.uint8)

# Fill with colors that exist in color2index
# Row 0: (0,0,0), (111,74,0), (81,0,81)
im[0, 0, :] = [0, 0, 0]
im[0, 1, :] = [111, 74, 0]
im[0, 2, :] = [81, 0, 81]

# Row 1: (128,64,128), (244,35,232), (250,170,160)
im[1, 0, :] = [128, 64, 128]
im[1, 1, :] = [244, 35, 232]
im[1, 2, :] = [250, 170, 160]

ARGS = {
    "im": im
}
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 3, dtype family int, shape (2, 3, 1) — shape (2, 3, 1) 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
load_pickle_file Ran
ran; our contract draft was wrong, not the code
jackaduma/CycleGAN-VC2/preprocess_training.py
code served (permissive licence) · get_code("1979c9d42c945db2")
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 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 pickle
import tempfile
import os

# Create a temporary pickle file with some data
temp_file = tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.pkl')
temp_filename = temp_file.name

# Write some sample data to the pickle file
sample_data = {
    'key1': 'value1',
    'key2': [1, 2, 3],
    'key3': {'nested': 'dict'}
}

with open(temp_filename, 'wb') as f:
    pickle.dump(sample_data, f)

ARGS = {
    'fileName': temp_filename
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 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
mean_std_loss Ran
ran, honoured the contract we drafted
NeuralVFX/lighting-swap-cyclegan/cycle_gan.py
pointer only (licence: NONE) · get_code("f41be69fddc4f6d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NeuralVFX/lighting-swap-cyclegan 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.

Rk Not yet run
unverified (harvested, no recorded run)
nahliabdelwahed/Face-Image-Deblurring/CycleGAN/CycleGAN_Code/ops.py
code served (permissive licence) · get_code("51b2bff753b420af")
How it ran

no invocation recorded.

c7s1_k Not yet run
unverified (harvested, no recorded run)
nahliabdelwahed/Face-Image-Deblurring/CycleGAN/CycleGAN_Code/ops.py
code served (permissive licence) · get_code("29c073d4bcd081b3")
How it ran

no invocation recorded.

c7s1_k Not yet run
unverified (harvested, no recorded run)
vanhuyz/CycleGAN-TensorFlow/ops.py
code served (permissive licence) · get_code("3547e76f546ea2fb")
How it ran

no invocation recorded.

calculate_activation_statistics Not yet run
unverified (harvested, no recorded run)
ranery/Bayesian-CycleGAN/evaluation/fid.py
code served (permissive licence) · get_code("91628fe016b3b141")
How it ran

no invocation recorded.

combined_flat_anneal Not yet run
unverified (harvested, no recorded run)
tmabraham/UPIT/upit/train/cyclegan.py
code served (permissive licence) · get_code("c2f38f10e9b9fd77")
How it ran

no invocation recorded.

compute_gradient_penalty Not yet run
unverified (harvested, no recorded run)
NiucunCode/Deep-Learning-proj2/stargan/stargan.py
pointer only (licence: NONE) · get_code("6150661478a11e4a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NiucunCode/Deep-Learning-proj2 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. No invocation recorded.

create_model Not yet run
unverified (harvested, no recorded run)
karl-hajjar/Generative-Adversarial-Networks/models.py
pointer only (licence: NONE) · get_code("c862e3a3a908331d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, karl-hajjar/Generative-Adversarial-Networks 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. No invocation recorded.

data_reader Not yet run
unverified (harvested, no recorded run)
nahliabdelwahed/Face-Image-Deblurring/CycleGAN/CycleGAN_Code/build_data.py
code served (permissive licence) · get_code("256590a5ff578f7e")
How it ran

no invocation recorded.

decode_image Not yet run
unverified (harvested, no recorded run)
yex666/cyclegan-in-mindspore/src/cyclegan_utils/tools.py
code served (permissive licence) · get_code("31276b5e652eac13")
How it ran

no invocation recorded.

define_G Not yet run
unverified (harvested, no recorded run)
ranery/Bayesian-CycleGAN/models/networks.py
code served (permissive licence) · get_code("d3aad42a142a67c5")
How it ran

no invocation recorded.

dk Not yet run
unverified (harvested, no recorded run)
nahliabdelwahed/Face-Image-Deblurring/CycleGAN/CycleGAN_Code/ops.py
code served (permissive licence) · get_code("5bd1e9f79cb2d533")
How it ran

no invocation recorded.

get_activations Not yet run
unverified (harvested, no recorded run)
ranery/Bayesian-CycleGAN/evaluation/fid.py
code served (permissive licence) · get_code("e22554578964be22")
How it ran

no invocation recorded.

get_discriminator Not yet run
unverified (harvested, no recorded run)
yex666/cyclegan-in-mindspore/src/models/cycle_gan.py
code served (permissive licence) · get_code("f8a056c53e46014b")
How it ran

no invocation recorded.

get_generator Not yet run
unverified (harvested, no recorded run)
yex666/cyclegan-in-mindspore/src/models/cycle_gan.py
code served (permissive licence) · get_code("9ba994b8bf7dcc37")
How it ran

no invocation recorded.

get_inception_score Not yet run
unverified (harvested, no recorded run)
ranery/Bayesian-CycleGAN/evaluation/inception_score.py
code served (permissive licence) · get_code("b49d09e26bebee3c")
How it ran

no invocation recorded.

get_random_sample Not yet run
unverified (harvested, no recorded run)
Adi-iitd/AI-Art/src/CycleGAN/CycleGAN-PL.py
code served (permissive licence) · get_code("9d9c3351e51a0871")
How it ran

no invocation recorded.

parse_args Not yet run
unverified (harvested, no recorded run)
yex666/cyclegan-in-mindspore/src/config/cyclegan_config.py
code served (permissive licence) · get_code("803e54320fbaee04")
How it ran

no invocation recorded.

Also present in other papers' code

Of 31 samples lifted from this paper's linked repositories, 31 carry a function identity and 0 do not. Of the 31 distinct functions with an identity, 8 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 6 later) and 23 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
calculate_frechet_distance 15 other papers
1 dated earlier, 14 later
1406.2661 (2014-06)
Generative Adversarial Networks
1706.08500 (2017-06)
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
1802.10551 (2018-02)
A Variational Inequality Perspective on Generative Adversarial Networks
and 12 more not named here
calculate_activation_statistics 12 other papers
1 dated earlier, 11 later
1406.2661 (2014-06)
Generative Adversarial Networks
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
1802.10551 (2018-02)
A Variational Inequality Perspective on Generative Adversarial Networks
and 9 more not named here
get_activations 9 other papers
9 later
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
1802.10551 (2018-02)
A Variational Inequality Perspective on Generative Adversarial Networks
1806.04326 (2018-06)
Differentiable Compositional Kernel Learning for Gaussian Processes
and 6 more not named here
load_pickle_file 3 other papers
1 dated earlier, 2 later
1610.04019 (2016-10)
Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder
1711.11293 (2017-11)
Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks
1904.04631 (2019-04)
CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion
compute_gradient_penalty 1 other paper
1 later
1711.09020 (2017-11)
StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
create_list 1 other paper
1 later
1806.02311 (2018-06)
Unsupervised Attention-guided Image to Image Translation
create_model 1 other paper
1 dated earlier
1701.07875 (2017-01)
Wasserstein GAN
get_random_sample 1 other paper
1 dated earlier
1508.06576 (2015-08)
A Neural Algorithm of Artistic Style

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

Repositories linked to this paper

More are linked than shown here.

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

Abstract

Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training data will not be available. We present an approach for learning to translate an image from a source domain $X$ to a target domain $Y$ in the absence of paired examples. Our goal is to learn a mapping $G: X \rightarrow Y$ such that the distribution of images from $G(X)$ is indistinguishable from the distribution $Y$ using an adversarial loss. Because this mapping is highly under-constrained, we couple it with an inverse mapping $F: Y \rightarrow X$ and introduce a cycle consistency loss to push $F(G(X)) \approx X$ (and vice versa). Qualitative results are presented on several tasks where paired training data does not exist, including collection style transfer, object transfiguration, season transfer, photo enhancement, etc. Quantitative comparisons against several prior methods demonstrate the superiority of our approach.

For agents

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

get_harvested_code_for_paper("1703.10593")
get_code_for_paper("1703.10593")
have("1703.10593")

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

curl https://syntology.ai/api/ran/1703.10593.json

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

[![Syntology run record](https://syntology.ai/api/ran/1703.10593.svg)](https://syntology.ai/paper/1703.10593)

Connect an agent — have() is free.