SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1809.11096 · 2018

Large Scale GAN Training for High Fidelity Natural Image Synthesis

Jeff Donahue, Karen Simonyan, Andrew Brock

arXiv · PDF · Open in the Atlas

Code that ran

28 of 41 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; 3 honoured the contract we drafted, 3 violated it and 7 have no contract verdict; 15 failures of our instrument; 13 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/1809.11096.json · badge: /api/ran/1809.11096.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
kidist-amde/biggan-pytorch community (classifier label)
classifier basis: plan_row
13 ran · 1 no recorded run
lucidrains/big-sleep community (classifier label)
classifier basis not recorded on the link
7 ran · 4 no recorded run
mingtaoguo/biggan-tensorflow community (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
luqui/big-sleep community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 2 no recorded run
taki0112/BigGAN-Tensorflow community (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
yaxingwang/DeepI2I extension (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
D_arch Ran
ran; our contract draft was wrong, not the code
kidist-amde/biggan-pytorch/BigGAN.py
pointer only (licence: MIT); the stored copy get_code serves, from VICO-UoE/IT-GAN, is pointer only (licence: NONE) · get_code("85eb95cce203dfc7")
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 VICO-UoE/IT-GAN, 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.

E_arch Ran
ran; our contract draft was wrong, not the code
yaxingwang/DeepI2I/DeepI2I_BigGAN/BigGAN.py
pointer only (licence: NONE) · get_code("c49b45bbb80fa489")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yaxingwang/DeepI2I 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.

G_arch Ran
ran; our contract draft was wrong, not the code
kidist-amde/biggan-pytorch/BigGAN.py
pointer only (licence: MIT); the stored copy get_code serves, from VICO-UoE/IT-GAN, is pointer only (licence: NONE) · get_code("e8c308c9283407d7")
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 VICO-UoE/IT-GAN, 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.

create_text_path Ran
ran on a synthesized input
lucidrains/big-sleep/big_sleep/big_sleep.py
code served (permissive licence) · get_code("7ce5c26b4ae6975e")
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
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - text: used as a string, concatenated directly
# - img: either None, a string (filename with extension), or something else (treated as PIL_img)
# - encoding: checked for None, if not None triggers special behavior
# The function performs string manipulations and returns a processed string

ARGS = {
    'text': 'sample_text',
    'img': 'image_file.jpg',
    'encoding': None
}
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 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
denorm Ran
ran; our contract draft was wrong, not the code
kidist-amde/biggan-pytorch/TFHub/biggan_v1.py
code served (permissive licence) · get_code("6e16337c88174e00")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function denorm takes a tensor x, applies (x + 1) / 2, and clamps to [0, 1]
# We need to provide a tensor that works with these operations

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
differentiable_topk Ran
ran on a synthesized input
lucidrains/big-sleep/big_sleep/big_sleep.py
code served (permissive licence) · get_code("6c9418cb364fc28e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small input tensor: batch_size=2, dim=4
x = torch.randn(2, 4)

# Set k to a value less than dim
k = 2

# Set temperature parameter
temperature = 1.0

ARGS = {
    "x": x,
    "k": k,
    "temperature": temperature,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
exists Ran
ran, violated the contract we drafted
lucidrains/big-sleep/big_sleep/big_sleep.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
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 ThomasMrY/VCT, 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.

find_classes Ran
ran; our contract draft was wrong, not the code
kidist-amde/biggan-pytorch/datasets.py
code served (permissive licence) · get_code("52d10a10fb72fb9f")
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 os
import tempfile
import shutil

# Create a temporary directory with some subdirectories to simulate a class directory structure
temp_dir = tempfile.mkdtemp()
os.makedirs(os.path.join(temp_dir, "class_a"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "class_b"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "class_c"), exist_ok=True)

ARGS = {
    "dir": temp_dir
}
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 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
get_embeddings_from_loader 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 uoguelph-mlrg/instance_selection_for_gans
pointer only; the stored copy get_code serves, from uoguelph-mlrg/instance_selection_for_gans, is pointer only (licence: NOASSERTION) · get_code("ff18ad392f262bf4")
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.

gram_schmidt Ran
ran; our contract draft was wrong, not the code
kidist-amde/biggan-pytorch/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from mshahbazi72/cGANTransfer, is pointer only (licence: NONE) · get_code("c41836f3e51fa8f1")
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 mshahbazi72/cGANTransfer, 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.

is_image_file Ran
ran, violated the contract we drafted
kidist-amde/biggan-pytorch/datasets.py
pointer only (licence: MIT); the stored copy get_code serves, from ermongroup/fairgen, is pointer only (licence: NONE) · get_code("4e6a8faaf8e44abe")
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 ermongroup/fairgen, 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.

l2normalize Ran
ran, violated the contract we drafted
kidist-amde/biggan-pytorch/TFHub/biggan_v1.py
code served (permissive licence) · get_code("9b11458d7d1ec61c")
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 1, dtype family float, shape (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)

# The function l2normalize takes a vector v and normalizes it by dividing by its norm + eps
# v needs to be a torch tensor with a .norm() method
# eps is a small float for numerical stability

v = torch.randn(4)

ARGS = {
    "v": v,
    "eps": 0.0001
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (4,) — shape (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
lanczos Ran
ran; our contract draft was wrong, not the code
lucidrains/big-sleep/big_sleep/resample.py
pointer only (licence: MIT); the stored copy get_code serves, from YvanG/VQGAN-CLIP, is pointer only (licence: NONE) · get_code("1c4b58a58ab65b12")
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 YvanG/VQGAN-CLIP, 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.

loss_dcgan_dis Ran
ran; our contract draft was wrong, not the code
kidist-amde/biggan-pytorch/losses.py
code served (permissive licence) · get_code("982a26492dc6b7fb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family 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 torch.nn.functional as F

torch.manual_seed(0)

# Create small discriminator output tensors
# dis_fake: discriminator output for fake samples
dis_fake = torch.randn(2, 4)

# dis_real: discriminator output for real samples
dis_real = torch.randn(2, 4)

ARGS = {
    "dis_fake": dis_fake,
    "dis_real": dis_real,
}
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 tuple, ndim 1, 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
loss_dcgan_gen Ran
ran; our contract draft was wrong, not the code
kidist-amde/biggan-pytorch/losses.py
code served (permissive licence) · get_code("6c34831223553b6f")
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 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.functional as F

torch.manual_seed(0)

# The function loss_dcgan_gen expects dis_fake, which is used with:
# - F.softplus() - expects a tensor
# - torch.mean() - expects a tensor
# So dis_fake should be a tensor

# Create a small fake discriminator output tensor (batch_size=2, some features)
dis_fake = torch.randn(2, 4)

ARGS = {
    "dis_fake": dis_fake,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 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
loss_hinge_dis Ran
ran; our contract draft was wrong, not the code
kidist-amde/biggan-pytorch/losses.py
code served (permissive licence) · get_code("290cd37ab0098d5c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family 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 torch.nn.functional as F

torch.manual_seed(0)

# The function loss_hinge_dis takes two tensor arguments:
# dis_fake and dis_real
# It computes relu-based hinge losses on them and returns a tuple of two scalars

# Create small discriminator output tensors (batch_size=2, arbitrary values)
dis_fake = torch.randn(2, 4)  # Fake discriminator scores
dis_real = torch.randn(2, 4)  # Real discriminator scores

ARGS = {
    "dis_fake": dis_fake,
    "dis_real": dis_real,
}
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 tuple, ndim 1, 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
make_dataset Ran
ran; our contract draft was wrong, not the code
kidist-amde/biggan-pytorch/datasets.py
pointer only (licence: MIT); the stored copy get_code serves, from ermongroup/fairgen, is pointer only (licence: NONE) · get_code("79e61b6269a450e8")
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 ermongroup/fairgen, 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.

normalize Ran
ran on a synthesized input
taki0112/BigGAN-Tensorflow/utils.py
code served (permissive licence) · get_code("da566c7a926c1dd3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function normalize takes a single parameter 'x' and performs arithmetic operations on it
# x should be a tensor or array-like object that supports division and subtraction
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 (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
permute_guidance Ran
ran on a synthesized input
luqui/big-sleep/slippery.py
code served (permissive licence) · get_code("6568dce1945cc36f")
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 bool, 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 random

def permute_guidance(guidance):
    prompt = set((s for s in guidance.get('prompt', '').split('\\') if s))
    avoid = set((s for s in guidance.get('avoid', '').split('\\') if s))
    keywords = set.union(prompt, avoid)
    if not keywords:
        return False
    new_prompt = prompt
    new_avoid = avoid
    while prompt == new_prompt and avoid == new_avoid:
        new_prompt = set((s for s in keywords if random.randrange(2)))
        new_avoid = set((s for s in keywords if s not in new_prompt))
        print(f'Generated {new_prompt} - {new_avoid}')
    guidance['prompt'] = '\\'.join(new_prompt)
    guidance['avoid'] = '\\'.join(new_avoid)
    return True

# Set seed for reproducibility
random.seed(42)

# Construct valid arguments
guidance = {
    'prompt': 'cat\\dog\\bird',
    'avoid': 'fish\\snake'
}

ARGS = {
    'guidance': guidance
}
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 bool, 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
power_iteration Ran
ran; our contract draft was wrong, not the code
kidist-amde/biggan-pytorch/layers.py
code served (permissive licence) · get_code("28d3a35157f2916d")
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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# Construct valid arguments for power_iteration
# W: weight matrix that will be multiplied with u and v vectors
# Shape should allow matmul operations: (4, 3) so u (1, 4) @ W (4, 3) = (1, 3)
W = torch.randn(4, 3)

# u_: list of initial vectors
# Each should be a 1D tensor with size matching W's first dimension
u_ = [
    torch.randn(1, 4),
    torch.randn(1, 4),
]

# update: boolean flag
update = True

# eps: small epsilon for numerical stability
eps = 1e-12

ARGS = {
    "W": W,
    "u_": u_,
    "update": update,
    "eps": eps,
}
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 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
ramp Ran
ran, honoured the contract we drafted
lucidrains/big-sleep/big_sleep/resample.py
pointer only (licence: MIT); the stored copy get_code serves, from YvanG/VQGAN-CLIP, is pointer only (licence: NONE) · get_code("8c580a6820115461")
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 YvanG/VQGAN-CLIP, 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.

read_catdog Ran
ran on a synthesized input
mingtaoguo/biggan-tensorflow/utils.py
code served (permissive licence) · get_code("3aadcca52d456283")
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

# Create synthetic data for the cat-dog dataset
# The function indexes into data and labels with integer arrays
# So we need arrays that support indexing with np.ndarray

# Create data array with shape (11078, 4) - 11078 samples, 4 features each
data = np.random.randn(11078, 4).astype(np.float32)

# Create labels array with shape (11078,) - one label per sample
labels = np.random.randint(0, 2, 11078)

# Batch size for sampling
batch_size = 2

ARGS = {
    "data": data,
    "labels": labels,
    "batch_size": batch_size
}
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 — 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
read_cifar Ran
ran on a synthesized input
mingtaoguo/biggan-tensorflow/utils.py
code served (permissive licence) · get_code("38c8fd67120015bd")
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 synthetic CIFAR-like data
# CIFAR-10 has 50000 training images of shape (32, 32, 3)
# We'll create tiny stand-in data
data = np.random.randint(0, 256, size=(50000, 4, 3), dtype=np.uint8)
labels = np.random.randint(0, 10, size=(50000,), dtype=np.int64)
batch_size = 2

ARGS = {
    "data": data,
    "labels": labels,
    "batch_size": batch_size,
}
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 — 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
sinc Ran
ran; our contract draft was wrong, not the code
lucidrains/big-sleep/big_sleep/resample.py
pointer only (licence: MIT); the stored copy get_code serves, from YvanG/VQGAN-CLIP, is pointer only (licence: NONE) · get_code("86a64cd8e1771cc5")
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 YvanG/VQGAN-CLIP, 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.

truncated_noise_sample Ran
ran, honoured the contract we drafted
mingtaoguo/biggan-tensorflow/utils.py
code served (permissive licence) · get_code("c19e800fac89b7b2")
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, 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 numpy as np
from scipy.stats import truncnorm

ARGS = {
    "batch_size": 2,
    "dim_z": 4,
    "truncation": 1.0,
    "seed": 42
}
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 ndarray, 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
truncated_z_sample Ran
ran, honoured the contract we drafted
kidist-amde/biggan-pytorch/TFHub/biggan_v1.py
code served (permissive licence) · get_code("b72f0c209b7b64be")
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, 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 numpy as np
from scipy.stats import truncnorm

ARGS = {
    "batch_size": 2,
    "z_dim": 4,
    "truncation": 0.5,
    "seed": 42,
}
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 ndarray, 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
underscorify Ran
ran on a synthesized input
luqui/big-sleep/big_sleep/big_sleep.py
code served (permissive licence) · get_code("4a5f2b9e54f4fd6c")
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 string
import re

def underscorify(value):
    no_punctuation = str(value.translate(str.maketrans('', '', string.punctuation)))
    spaces_to_one_underline = re.sub('[-\\s]+', '_', no_punctuation).strip('-_')
    return spaces_to_one_underline

ARGS = {
    'value': 'Hello, World! -- This is a test.'
}
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
url_to_filename Ran
ran; our contract draft was wrong, not the code
lucidrains/big-sleep/big_sleep/biggan.py
code served (permissive licence) · get_code("5eff22fa0a651276")
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.

from hashlib import sha256

ARGS = {
    "url": "https://example.com/model/checkpoint.bin",
    "etag": "abc123def456"
}
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
build_model Not yet run
unverified (harvested, no recorded run)
lucidrains/big-sleep/big_sleep/clip.py
code served (permissive licence) · get_code("2d6984fd14c32184")
How it ran

no invocation recorded.

cached_path Not yet run
unverified (harvested, no recorded run)
lucidrains/big-sleep/big_sleep/biggan.py
code served (permissive licence) · get_code("9dba35ef1c6281eb")
How it ran

no invocation recorded.

conditional_batchnorm Not yet run
unverified (harvested, no recorded run)
mingtaoguo/biggan-tensorflow/ops.py
code served (permissive licence) · get_code("8fd36edeb5ac19db")
How it ran

no invocation recorded.

conv Not yet run
unverified (harvested, no recorded run)
mingtaoguo/biggan-tensorflow/ops.py
code served (permissive licence) · get_code("0fe7078e87e1115e")
How it ran

no invocation recorded.

filename_to_url Not yet run
unverified (harvested, no recorded run)
lucidrains/big-sleep/big_sleep/biggan.py
code served (permissive licence) · get_code("c5ba2abfbf6a9dfa")
How it ran

no invocation recorded.

get_embedder Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from uoguelph-mlrg/instance_selection_for_gans
pointer only; the stored copy get_code serves, from uoguelph-mlrg/instance_selection_for_gans, is pointer only (licence: NOASSERTION) · get_code("8c0803be6096a937")
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.

get_keep_indices Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from uoguelph-mlrg/instance_selection_for_gans
pointer only; the stored copy get_code serves, from uoguelph-mlrg/instance_selection_for_gans, is pointer only (licence: NOASSERTION) · get_code("ed9e5e2f2a6ec523")
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.

load Not yet run
unverified (harvested, no recorded run)
lucidrains/big-sleep/big_sleep/clip.py
code served (permissive licence) · get_code("b5b26b1bb3d408a5")
How it ran

no invocation recorded.

load Not yet run
unverified (harvested, no recorded run)
luqui/big-sleep/big_sleep/clip.py
code served (permissive licence) · get_code("3d58ef750e04cfc8")
How it ran

no invocation recorded.

load_data Not yet run
unverified (harvested, no recorded run)
taki0112/BigGAN-Tensorflow/utils.py
code served (permissive licence) · get_code("480dc6bdc031d794")
How it ran

no invocation recorded.

non_local Not yet run
unverified (harvested, no recorded run)
mingtaoguo/biggan-tensorflow/ops.py
code served (permissive licence) · get_code("f4b3879c22631581")
How it ran

no invocation recorded.

preprocessing Not yet run
unverified (harvested, no recorded run)
taki0112/BigGAN-Tensorflow/utils.py
code served (permissive licence) · get_code("7c108866402e9866")
How it ran

no invocation recorded.

proj Not yet run
unverified (harvested, no recorded run)
kidist-amde/biggan-pytorch/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from mshahbazi72/cGANTransfer, is pointer only (licence: NONE) · get_code("4015ab1f3ab9b881")
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 mshahbazi72/cGANTransfer, 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. No invocation recorded.

Also present in other papers' code

Of 41 samples lifted from this paper's linked repositories, 41 carry a function identity and 0 do not. Of the 40 distinct functions with an identity, 26 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 2 the same month, 26 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
exists 486 other papers
3 dated earlier, 481 later, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
build_model 119 other papers
117 later, 2 undated
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2104.14294 (2021-04)
Emerging Properties in Self-Supervised Vision Transformers
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
and 116 more not named here
url_to_filename 48 other papers
1 dated earlier, 47 later · 8 only as an assembly brick
1610.02424 (2016-10)
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
and 45 more not named here
find_classes 30 other papers
2 dated earlier, 1 the same month, 27 later
1406.2661 (2014-06)
Generative Adversarial Networks
1612.06321 (2016-12)
Large-Scale Image Retrieval with Attentive Deep Local Features
1809.04729 (2018-09)
A Less Biased Evaluation of Out-of-distribution Sample Detectors
and 27 more not named here
gram_schmidt 28 other papers
28 later · 5 only as an assembly brick
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1910.05852 (2019-10)
Implicit competitive regularization in GANs
1912.00953 (2019-12)
LOGAN: Latent Optimisation for Generative Adversarial Networks
and 25 more not named here
proj 28 other papers
28 later · 5 only as an assembly brick
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1910.05852 (2019-10)
Implicit competitive regularization in GANs
1912.00953 (2019-12)
LOGAN: Latent Optimisation for Generative Adversarial Networks
and 25 more not named here
power_iteration 25 other papers
25 later · 5 only as an assembly brick
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1910.05852 (2019-10)
Implicit competitive regularization in GANs
1912.00953 (2019-12)
LOGAN: Latent Optimisation for Generative Adversarial Networks
and 22 more not named here
is_image_file 22 other papers
3 dated earlier, 1 the same month, 18 later
1406.2661 (2014-06)
Generative Adversarial Networks
1603.08511 (2016-03)
Colorful Image Colorization
1805.08318 (2018-05)
Self-Attention Generative Adversarial Networks
and 19 more not named here
G_arch 18 other papers
18 later · 3 only as an assembly brick
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
2003.13659 (2020-03)
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
and 15 more not named here
D_arch 15 other papers
15 later
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
2003.13659 (2020-03)
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
and 12 more not named here
loss_hinge_dis 11 other papers
11 later
1912.00953 (2019-12)
LOGAN: Latent Optimisation for Generative Adversarial Networks
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
2008.10599 (2020-08)
The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
and 8 more not named here
loss_dcgan_dis 10 other papers
10 later
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
2008.10599 (2020-08)
The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
2108.07668 (2021-08)
Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
and 7 more not named here
make_dataset 10 other papers
1 dated earlier, 9 later
1406.2661 (2014-06)
Generative Adversarial Networks
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
2004.00917 (2020-04)
Controllable Orthogonalization in Training DNNs
and 7 more not named here
loss_dcgan_gen 9 other papers
9 later
2008.10599 (2020-08)
The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
2108.07668 (2021-08)
Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
aaai_20247 (2022 (year only))
An Adversarial Framework for Generating Unseen Images by Activation Maximization
and 6 more not named here
denorm 5 other papers
1 dated earlier, 4 later
1805.08318 (2018-05)
Self-Attention Generative Adversarial Networks
2010.02637 (2020-10)
Weakly Supervised Disentangled Generative Causal Representation Learning
2201.12179 (2022-01)
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
and 2 more not named here
cached_path 2 other papers
2 later
2206.00048 (2022-06)
PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs
2302.02451 (2023-02)
KDEformer: Accelerating Transformers via Kernel Density Estimation
filename_to_url 2 other papers
2 later
2206.00048 (2022-06)
PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs
2302.02451 (2023-02)
KDEformer: Accelerating Transformers via Kernel Density Estimation
l2normalize 2 other papers
1 dated earlier, 1 later
1802.05957 (2018-02)
Spectral Normalization for Generative Adversarial Networks
2201.12179 (2022-01)
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
lanczos 2 other papers
2 later
2103.00020 (2021-03)
Learning Transferable Visual Models From Natural Language Supervision
2204.08583 (2022-04)
VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance
ramp 2 other papers
2 later
2103.00020 (2021-03)
Learning Transferable Visual Models From Natural Language Supervision
2204.08583 (2022-04)
VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance

Shown: the 20 functions present in the most other papers. 6 more shared functions are not listed here.

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

Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal. To this end, we train Generative Adversarial Networks at the largest scale yet attempted, and study the instabilities specific to such scale. We find that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input. Our modifications lead to models which set the new state of the art in class-conditional image synthesis. When trained on ImageNet at 128×128 resolution, our models (BigGANs) achieve an Inception Score (IS) of 166.5 and Fréchet Inception Distance (FID) of 7.4, improving over the previous best IS of 52.52 and FID of 18.65.

For agents

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

get_harvested_code_for_paper("1809.11096")
get_code_for_paper("1809.11096")
have("1809.11096")

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

curl https://syntology.ai/api/ran/1809.11096.json

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

[![Syntology run record](https://syntology.ai/api/ran/1809.11096.svg)](https://syntology.ai/paper/1809.11096)

Connect an agent — have() is free.