SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.05338 · 2020

On Data Augmentation for GAN Training

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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 4 have no contract verdict; 0 failures of our instrument; 3 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/2006.05338.json · badge: /api/ran/2006.05338.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
sutd-visual-computing-group/dag-gans canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
FunctionStatusWhere it lives
cropping Ran
ran on a synthesized input
sutd-visual-computing-group/dag-gans/pytorch/utils.py
code served (permissive licence) · get_code("489ea2ee97e637e3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 5, 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
import numpy as np

torch.manual_seed(0)

# Create a small tensor with distinct dimensions for batch, channels, height, width
x = torch.randn(2, 4, 16, 12)  # batch=2, channels=4, height=16, width=12

# aug parameter - reading the function body, it's not actually used
# but we need to provide it as it's a parameter
aug = None

ARGS = {
    "x": x,
    "aug": aug
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 5, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
fliprot Ran
ran on a synthesized input
sutd-visual-computing-group/dag-gans/pytorch/utils.py
code served (permissive licence) · get_code("377c58a4abeba1c6")
How it ran

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

import torch

torch.manual_seed(0)

# x is a tensor that gets flipped and transposed
# The function calls: x.flip(2), x.flip(3), x.transpose(2, 3).flip(2)
# So x needs at least 4 dimensions
# Let's create a 4D tensor: (batch, channels, height, width)
x = torch.randn(2, 3, 4, 5)

# aug is not actually used in the function body
aug = None

ARGS = {
    "x": x,
    "aug": aug,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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
fliprot Ran
ran on a synthesized input
sutd-visual-computing-group/dag-gans/tensorflow/utils.py
code served (permissive licence) · get_code("c6d26a555f1021f7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 5, 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 tensorflow as tf
import numpy as np

# Create a small image tensor for testing
# Shape: (batch_size, height, width, channels)
x = tf.constant(np.random.randn(2, 4, 3, 3).astype(np.float32))

# The 'aug' parameter is used but not directly accessed in the function body
# It's just passed through, so we can use any value
aug = None

ARGS = {
    'x': x,
    'aug': aug
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 5, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rotation Ran
ran on a synthesized input
sutd-visual-computing-group/dag-gans/pytorch/utils.py
code served (permissive licence) · get_code("a5418a6b54ead8e0")
How it ran

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

import torch

torch.manual_seed(0)

# The function rotates a tensor x by angles specified in degs
# x is a tensor with at least 4 dimensions (indexing dims 2 and 3)
# degs is a list/iterable of rotation angles (0, 90, 180, 270)

x = torch.randn(2, 4, 3, 5)  # batch=2, channels=4, height=3, width=5
degs = [0, 90, 180, 270]

ARGS = {
    "x": x,
    "degs": degs,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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_n_augments_from_policy Not yet run
unverified (harvested, no recorded run)
sutd-visual-computing-group/dag-gans/tensorflow/dag.py
code served (permissive licence) · get_code("ffe6e59df597b2d4")
How it ran

no invocation recorded.

image_crop Not yet run
unverified (harvested, no recorded run)
sutd-visual-computing-group/dag-gans/tensorflow/utils.py
code served (permissive licence) · get_code("67be61a69860ba1c")
How it ran

no invocation recorded.

rotation Not yet run
unverified (harvested, no recorded run)
sutd-visual-computing-group/dag-gans/tensorflow/utils.py
code served (permissive licence) · get_code("db6dd49f9dfced2f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 7 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.

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

Recent successes in Generative Adversarial Networks (GAN) have affirmed the importance of using more data in GAN training. Yet it is expensive to collect data in many domains such as medical applications. Data Augmentation (DA) has been applied in these applications. In this work, we first argue that the classical DA approach could mislead the generator to learn the distribution of the augmented data, which could be different from that of the original data. We then propose a principled framework, termed Data Augmentation Optimized for GAN (DAG), to enable the use of augmented data in GAN training to improve the learning of the original distribution. We provide theoretical analysis to show that using our proposed DAG aligns with the original GAN in minimizing the Jensen-Shannon (JS) divergence between the original distribution and model distribution. Importantly, the proposed DAG effectively leverages the augmented data to improve the learning of discriminator and generator. We conduct experiments to apply DAG to different GAN models: unconditional GAN, conditional GAN, self-supervised GAN and CycleGAN using datasets of natural images and medical images. The results show that DAG achieves consistent and considerable improvements across these models. Furthermore, when DAG is used in some GAN models, the system establishes state-of-the-art Frechet Inception Distance (FID) scores. Our code is available.

For agents

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

get_harvested_code_for_paper("2006.05338")
get_code_for_paper("2006.05338")
have("2006.05338")

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

curl https://syntology.ai/api/ran/2006.05338.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.05338.svg)](https://syntology.ai/paper/2006.05338)

Connect an agent — have() is free.