SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1701.07875 · 2017

Wasserstein GAN

arXiv · PDF · Open in the Atlas

Code that ran

16 of 22 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 12 failures of our instrument; 6 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/1701.07875.json · badge: /api/ran/1701.07875.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
copy not recorded community
not in the paper's declared repositories
4 ran · 1 no recorded run
rmyhovych/wgan reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
safwankdb/Wasserstein-GAN reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
shekkizh/WassersteinGAN.tensorflow community (classifier label)
classifier basis not recorded on the link
2 ran · 3 no recorded run
MaximeVandegar/Papers-in-100-Lines-of-Code reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
shahbuland/basic-gans reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
daheyinyin/wgan community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
W_Loss Ran
ran; our contract draft was wrong, not the code
shahbuland/basic-gans/GP-WGAN-pytorch.py
pointer only (licence: NONE) · get_code("1ed8e07513aa3597")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shahbuland/basic-gans 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.

create_image_lists Ran
ran on a synthesized input
shekkizh/WassersteinGAN.tensorflow/Dataset_Reader/read_celebADataset.py
code served (permissive licence) · get_code("b5c1644a78d48827")
How it ran

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

import os
import tempfile
import shutil
from PIL import Image

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

# Create subdirectory for images
image_subdir = os.path.join(temp_dir, 'images')
os.makedirs(image_subdir, exist_ok=True)

# Create some dummy JPEG files
for i in range(10):
    img = Image.new('RGB', (100, 100), color=(i*25, i*25, i*25))
    img.save(os.path.join(image_subdir, f'image_{i}.jpg'))

# Define arguments for the function
ARGS = {
    'image_dir': image_subdir,
    'testing_percentage': 0.2,
    'validation_percentage': 0.2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, tensorflow — 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
gallery Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from korra141/Generative-Adversarial-Networks
pointer only; the stored copy get_code serves, from korra141/Generative-Adversarial-Networks, is pointer only (licence: NONE) · get_code("278a4cc6c445af9d")
How it ran

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

generator_loss Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from donand/GAN_pytorch
pointer only; the stored copy get_code serves, from donand/GAN_pytorch, is pointer only (licence: NONE) · get_code("bedb8cd7ec02640d")
How it ran

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

get_args Ran
ran on a synthesized input
daheyinyin/wgan/src/args.py
code served (permissive licence) · get_code("49ea509ebb1d3590")
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 torch
import torch.nn as nn
import argparse
import tempfile
import os

# Create temporary directories for paths
temp_dir = tempfile.mkdtemp()
config_file = os.path.join(temp_dir, "config.json")
ckpt_file = os.path.join(temp_dir, "model.ckpt")
onnx_file = os.path.join(temp_dir, "model.onnx")
output_dir = os.path.join(temp_dir, "output")

# Create dummy files
with open(config_file, 'w') as f:
    f.write('{}')
with open(ckpt_file, 'w') as f:
    f.write('')
with open(onnx_file, 'w') as f:
    f.write('')
os.makedirs(output_dir, exist_ok=True)

# Define ARGS mapping for different phases
ARGS = {
    'phase': 'train'
}
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 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
latent_lerp Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from joeylitalien/celeba-gan-pytorch
pointer only; the stored copy get_code serves, from joeylitalien/celeba-gan-pytorch, is pointer only (licence: NONE) · get_code("ed31414e5c54cdd9")
How it ran

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

loss_mod_f_disc Ran
ran; our contract draft was wrong, not the code
rmyhovych/wgan/wgan.py
pointer only (licence: NONE) · get_code("54c81a1299e9981e")
How it ran

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

loss_mod_f_gen Ran
ran; our contract draft was wrong, not the code
rmyhovych/wgan/wgan.py
pointer only (licence: NONE) · get_code("cdc18420f3a1336d")
How it ran

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

loss_wasserstein_f_gen Ran
ran; our contract draft was wrong, not the code
rmyhovych/wgan/wgan.py
pointer only (licence: NONE) · get_code("b791fcf70f47f853")
How it ran

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

moving_average Ran
ran; our contract draft was wrong, not the code
MaximeVandegar/Papers-in-100-Lines-of-Code/Wasserstein_GAN/wgan.py
code served (permissive licence) · get_code("8b7e4c7f96e7694c")
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 ndarray, ndim 1, dtype family float, shape (8,) 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 data for moving average
data = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0])
window_size = 3

ARGS = {
    "data": data,
    "window_size": window_size
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 1, dtype family float, shape (8,) — shape (8,) 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
noise Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
safwankdb/Wasserstein-GAN/wgan.py
pointer only (licence: NONE) · get_code("9dd51c421620b70a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, safwankdb/Wasserstein-GAN 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.

read_dataset Ran
ran on a synthesized input
shekkizh/WassersteinGAN.tensorflow/Dataset_Reader/read_celebADataset.py
code served (permissive licence) · get_code("239b602d01815085")
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 CelebA_Dataset. 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 os
import tempfile
import shutil
from six.moves import cPickle as pickle

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

# Create a mock image directory structure with some dummy files
image_dir = os.path.join(temp_dir, 'img_align_celeba')
os.makedirs(image_dir, exist_ok=True)

# Create some dummy image files
for i in range(10):
    dummy_file = os.path.join(image_dir, f'image_{i}.jpg')
    with open(dummy_file, 'wb') as f:
        f.write(b'dummy image data')

# Pre-create the pickle file so read_dataset finds it
pickle_filename = 'celebA.pickle'
pickle_filepath = os.path.join(temp_dir, pickle_filename)

# Create mock image lists
mock_result = {
    'train': [os.path.join(image_dir, f'image_{i}.jpg') for i in range(7)],
    'test': [os.path.join(image_dir, f'image_{i}.jpg') for i in range(7, 9)],
    'validation': [os.path.join(image_dir, f'image_{i}.jpg') for i in range(9, 10)]
}

# Pickle the mock data
with open(pickle_filepath, 'wb') as f:
    pickle.dump(mock_result, f, pickle.HIGHEST_PROTOCOL)

ARGS = {
    'data_dir': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
six, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CelebA_Dataset — a CelebA_Dataset output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CelebA_Dataset 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
sample_noise Ran
ran, honoured the contract we drafted
MaximeVandegar/Papers-in-100-Lines-of-Code/Wasserstein_GAN/wgan.py
code served (permissive licence) · get_code("561c628f77383ba9")
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 4, dtype family float, shape (2, 100, 1, 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 torch

torch.manual_seed(0)

ARGS = {
    'batch_size': 2,
    'device': torch.device('cpu')
}
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 4, dtype family float, shape (2, 100, 1, 1) — shape (2, 100, 1, 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
screen_lerp Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from joeylitalien/celeba-gan-pytorch
pointer only; the stored copy get_code serves, from joeylitalien/celeba-gan-pytorch, is pointer only (licence: NONE) · get_code("33614cf1f2bf5b64")
How it ran

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

train_critic Ran
ran; our contract draft was wrong, not the code
safwankdb/Wasserstein-GAN/wgan.py
pointer only (licence: NONE) · get_code("58b3f3f3f2089fb2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, safwankdb/Wasserstein-GAN 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.

train_generator Ran
ran; our contract draft was wrong, not the code
safwankdb/Wasserstein-GAN/wgan.py
pointer only (licence: NONE) · get_code("4e21586ab54e8180")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, safwankdb/Wasserstein-GAN 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.

GP_Loss Not yet run
unverified (harvested, no recorded run)
shahbuland/basic-gans/GP-WGAN-pytorch.py
pointer only (licence: NONE) · get_code("e6c64901f2937406")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shahbuland/basic-gans 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)
this paper's copy was not recorded; identical code first harvested from karl-hajjar/Generative-Adversarial-Networks
pointer only; the stored copy get_code serves, from karl-hajjar/Generative-Adversarial-Networks, is pointer only (licence: NONE) · get_code("c862e3a3a908331d")
How it ran

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

train Not yet run
unverified (harvested, no recorded run)
MaximeVandegar/Papers-in-100-Lines-of-Code/Wasserstein_GAN/wgan.py
code served (permissive licence) · get_code("53065998bed260c3")
How it ran

no invocation recorded.

weight_variable Not yet run
unverified (harvested, no recorded run)
shekkizh/WassersteinGAN.tensorflow/utils.py
code served (permissive licence) · get_code("b1cce189d8a4c490")
How it ran

no invocation recorded.

weight_variable_xavier_initialized Not yet run
unverified (harvested, no recorded run)
shekkizh/WassersteinGAN.tensorflow/utils.py
code served (permissive licence) · get_code("4fca58134a4f0785")
How it ran

no invocation recorded.

xavier_init Not yet run
unverified (harvested, no recorded run)
shekkizh/WassersteinGAN.tensorflow/utils.py
code served (permissive licence) · get_code("5645c84de7678d1e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 22 samples lifted from this paper's linked repositories, 22 carry a function identity and 0 do not. Of the 22 distinct functions with an identity, 8 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 3 later) and 14 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
xavier_init 4 other papers
1 dated earlier, 3 later
1604.07379 (2016-04)
Context Encoders: Feature Learning by Inpainting
1703.01488 (2017-03)
Autoencoding Variational Inference For Topic Models
1909.06296 (2019-09)
Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy
and 1 more not named here
GP_Loss 1 other paper
1 later
1704.00028 (2017-04)
Improved Training of Wasserstein GANs
create_model 1 other paper
1 later
1703.10593 (2017-03)
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
gallery 1 other paper
1 dated earlier
1406.2661 (2014-06)
Generative Adversarial Networks
generator_loss 1 other paper
1 dated earlier
1406.2661 (2014-06)
Generative Adversarial Networks
latent_lerp 1 other paper
1 dated earlier
1406.2661 (2014-06)
Generative Adversarial Networks
screen_lerp 1 other paper
1 dated earlier
1406.2661 (2014-06)
Generative Adversarial Networks
weight_variable_xavier_initialized 1 other paper
1 dated earlier
1604.07379 (2016-04)
Context Encoders: Feature Learning by Inpainting

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

We introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches. Furthermore, we show that the corresponding optimization problem is sound, and provide extensive theoretical work highlighting the deep connections to other distances between distributions.

For agents

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

get_harvested_code_for_paper("1701.07875")
get_code_for_paper("1701.07875")
have("1701.07875")

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

curl https://syntology.ai/api/ran/1701.07875.json

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

[![Syntology run record](https://syntology.ai/api/ran/1701.07875.svg)](https://syntology.ai/paper/1701.07875)

Connect an agent — have() is free.