SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1807.04720 · 2018

A Large-Scale Study on Regularization and Normalization in GANs

arXiv · PDF · Open in the Atlas

Code that ran

10 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 3 failures of our instrument; 5 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/1807.04720.json · badge: /api/ran/1807.04720.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
xiao7199/compare_gan community (classifier label)
classifier basis not recorded on the link
6 ran · 5 no recorded run
w510056105/DeepLearning community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
FSpecialGauss Ran
ran on a synthesized input
xiao7199/compare_gan/compare_gan/src/image_similarity.py
pointer only (licence: Apache-2.0) · get_code("980a02883b50afd3")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, xiao7199/compare_gan, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

GetDefaultParams Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from blessengeorge/compare_gan
pointer only · get_code("a3c9ee0e5a930a73")
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.

VerifyCompatibleImageShapes Ran
ran on a synthesized input
xiao7199/compare_gan/compare_gan/src/image_similarity.py
pointer only (licence: Apache-2.0) · get_code("caf55addd2a79ff2")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, xiao7199/compare_gan, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

analyze_jacobian Ran
ran on a synthesized input
xiao7199/compare_gan/compare_gan/src/jacobian_conditioning.py
pointer only (licence: Apache-2.0) · get_code("df48993045f1fb99")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, xiao7199/compare_gan, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_prd Ran
ran on a synthesized input
xiao7199/compare_gan/compare_gan/src/prd_score.py
pointer only (licence: Apache-2.0) · get_code("91b26d9e0c4aab9b")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, xiao7199/compare_gan, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_prd_from_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xiao7199/compare_gan/compare_gan/src/prd_score.py
pointer only (licence: Apache-2.0) · get_code("0fd2f6b430b748c0")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, xiao7199/compare_gan, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_image_lists Ran
ran on a synthesized input
w510056105/DeepLearning/Projects/TransferLearning/InceptionV3_TransferLearning.py
code served (permissive licence) · get_code("af5a5c1e5be254a9")
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
import numpy as np

# Create a temporary directory structure with sample image files
temp_dir = tempfile.mkdtemp()
input_data = os.path.join(temp_dir, 'data', 'flower_photos')
os.makedirs(input_data, exist_ok=True)

# Create subdirectories for different flower types
flower_types = ['roses', 'tulips', 'sunflowers']
for flower_type in flower_types:
    flower_dir = os.path.join(input_data, flower_type)
    os.makedirs(flower_dir, exist_ok=True)
    
    # Create some dummy image files
    for i in range(10):
        for ext in ['jpg', 'jpeg']:
            file_path = os.path.join(flower_dir, f'image_{i}.{ext}')
            with open(file_path, 'w') as f:
                f.write('dummy')

# Monkey-patch the INPUT_DATA in the module
import sys
import types
module_code = """
import glob
import os.path
import numpy as np

INPUT_DATA = '{}'

def create_image_lists(validation_percentage, test_percentage):
    result = {{}}
    sub_dirs = [x[0] for x in os.walk(INPUT_DATA)]
    is_root_dir = True
    for sub_dir in sub_dirs:
        if is_root_dir:
            is_root_dir = False
            continue
        extensions = {{'jpg', 'jpeg', 'JPG', 'JPEG'}}
        file_list = []
        dir_name = os.path.basename(sub_dir)
        for extension in extensions:
            file_glob = os.path.join(INPUT_DATA, dir_name, '*.' + extension)
            file_list.extend(glob.glob(file_glob))
        if not file_list:
            continue
        label_name = dir_name.lower()
        training_images = []
        testing_images = []
        validation_images = []
        for file_name in file_list:
            base_name = os.path.basename(file_name)
            chance = np.random.randint(100)
            if chance < validation_percentage:
                validation_images.append(base_name)
            elif chance < validation_percentage + test_percentage:
                testing_images.append(base_name)
            else:
                training_images.append(base_name)
        result[label_name] = {{'dir': dir_name, 'training': training_images, 'testing': testing_images, 'validation': validation_images}}
    return result
""".format(input_data)

exec(module_code, globals())

ARGS = {
    'validation_percentage': 10,
    'test_percentage': 10
}
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 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
get_bottleneck_path Ran
ran on a synthesized input
w510056105/DeepLearning/Projects/TransferLearning/InceptionV3_TransferLearning.py
code served (permissive licence) · get_code("32bda22aba147afb")
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 os.path

CACHE_DIR = 'data/tmp/bottleneck'

def get_image_path(image_lists, image_dir, label_name, index, category):
    label_lists = image_lists[label_name]
    category_lists = label_lists[category]
    mod_index = index % len(category_lists)
    base_name = category_lists[mod_index]
    sub_dir = label_lists['dir']
    full_path = os.path.join(image_dir, sub_dir, base_name)
    return full_path

def get_bottleneck_path(image_lists, label_name, index, category):
    return get_image_path(image_lists, CACHE_DIR, label_name, index, category) + '.txt'

image_lists = {
    'cat': {
        'dir': 'cats_subdir',
        'training': ['cat1.jpg', 'cat2.jpg', 'cat3.jpg'],
        'validation': ['cat4.jpg', 'cat5.jpg'],
        'testing': ['cat6.jpg']
    },
    'dog': {
        'dir': 'dogs_subdir',
        'training': ['dog1.jpg', 'dog2.jpg'],
        'validation': ['dog3.jpg'],
        'testing': ['dog4.jpg', 'dog5.jpg', 'dog6.jpg']
    }
}

ARGS = {
    'image_lists': image_lists,
    'label_name': 'cat',
    'index': 0,
    'category': 'training'
}
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 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
get_image_path Ran
ran on a synthesized input
w510056105/DeepLearning/Projects/TransferLearning/InceptionV3_TransferLearning.py
code served (permissive licence) · get_code("124ce005185e25a3")
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 os.path

# Construct the image_lists structure expected by the function
image_lists = {
    'label1': {
        'training': ['image1.jpg', 'image2.jpg', 'image3.jpg'],
        'validation': ['image4.jpg', 'image5.jpg'],
        'testing': ['image6.jpg'],
        'dir': 'label1_subfolder'
    },
    'label2': {
        'training': ['image7.jpg', 'image8.jpg'],
        'validation': ['image9.jpg'],
        'testing': ['image10.jpg', 'image11.jpg', 'image12.jpg'],
        'dir': 'label2_subfolder'
    }
}

ARGS = {
    'image_lists': image_lists,
    'image_dir': '/data/images',
    'label_name': 'label1',
    'index': 5,
    'category': 'training'
}
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 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
prd_to_max_f_beta_pair Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xiao7199/compare_gan/compare_gan/src/prd_score.py
pointer only (licence: Apache-2.0) · get_code("5adbefd0ebfa3e5e")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, xiao7199/compare_gan, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

MultiscaleSSIM Not yet run
unverified (harvested, no recorded run)
xiao7199/compare_gan/compare_gan/src/image_similarity.py
pointer only (licence: Apache-2.0) · get_code("91e52735a9a4ef77")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, xiao7199/compare_gan, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

compute_jacobian Not yet run
unverified (harvested, no recorded run)
xiao7199/compare_gan/compare_gan/src/jacobian_conditioning.py
pointer only (licence: Apache-2.0) · get_code("d088682165b591d6")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, xiao7199/compare_gan, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

kid Not yet run
unverified (harvested, no recorded run)
xiao7199/compare_gan/compare_gan/src/kid_score.py
pointer only (licence: Apache-2.0) · get_code("023f8427ea56eaec")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, xiao7199/compare_gan, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

unpack_png_image Not yet run
unverified (harvested, no recorded run)
xiao7199/compare_gan/compare_gan/src/datasets.py
pointer only (licence: Apache-2.0) · get_code("d5d2e5cba8355657")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, xiao7199/compare_gan, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

unpack_raw_image Not yet run
unverified (harvested, no recorded run)
xiao7199/compare_gan/compare_gan/src/datasets.py
pointer only (licence: Apache-2.0) · get_code("7c6a1c5735f9a270")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, xiao7199/compare_gan, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 later) and 12 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
compute_prd_from_embedding 3 other papers
1 dated earlier, 2 later
1806.00035 (2018-06)
Assessing Generative Models via Precision and Recall
1905.10485 (2019-05)
Generative Latent Flow
2010.15639 (2020-10)
Teaching a GAN What Not to Learn
prd_to_max_f_beta_pair 3 other papers
1 dated earlier, 2 later
1806.00035 (2018-06)
Assessing Generative Models via Precision and Recall
1905.10485 (2019-05)
Generative Latent Flow
2010.15639 (2020-10)
Teaching a GAN What Not to Learn
GetDefaultParams 1 other paper
1 dated earlier
1711.10337 (2017-11)
Are GANs Created Equal? A Large-Scale Study

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

Generative adversarial networks (GANs) are a class of deep generative models which aim to learn a target distribution in an unsupervised fashion. While they were successfully applied to many problems, training a GAN is a notoriously challenging task and requires a significant number of hyperparameter tuning, neural architecture engineering, and a non-trivial amount of "tricks". The success in many practical applications coupled with the lack of a measure to quantify the failure modes of GANs resulted in a plethora of proposed losses, regularization and normalization schemes, as well as neural architectures. In this work we take a sober view of the current state of GANs from a practical perspective. We discuss and evaluate common pitfalls and reproducibility issues, open-source our code on Github, and provide pre-trained models on TensorFlow Hub.

For agents

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

get_harvested_code_for_paper("1807.04720")
get_code_for_paper("1807.04720")
have("1807.04720")

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

curl https://syntology.ai/api/ran/1807.04720.json

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

[![Syntology run record](https://syntology.ai/api/ran/1807.04720.svg)](https://syntology.ai/paper/1807.04720)

Connect an agent — have() is free.