SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1802.05637 · 2018

cGANs with Projection Discriminator

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 2 violated it and 1 has no contract verdict; 5 failures of our instrument; 0 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/1802.05637.json · badge: /api/ran/1802.05637.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
6 ran · 0 no recorded run
crcrpar/pytorch.sngan_projection reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
XHChen0528/SNGAN_Projection_Pytorch community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
adversarial_loss_d Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from simon0987/ACGAN-implemented-with-pytorch
pointer only; the stored copy get_code serves, from simon0987/ACGAN-implemented-with-pytorch, is pointer only (licence: NONE) · get_code("5507a6f1c680f8cb")
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.

adversarial_loss_g Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from simon0987/ACGAN-implemented-with-pytorch
pointer only; the stored copy get_code serves, from simon0987/ACGAN-implemented-with-pytorch, is pointer only (licence: NONE) · get_code("9464a3295e71013d")
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.

create_optimizer 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 DanielLongo/cGANs
pointer only; the stored copy get_code serves, from DanielLongo/cGANs, is pointer only (licence: NONE) · get_code("1260620e5bfe1614")
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.

discriminator_loss Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from DanielLongo/cGANs
pointer only; the stored copy get_code serves, from DanielLongo/cGANs, is pointer only (licence: NONE) · get_code("8d99aaa30d71b315")
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.

generate_nosie Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from DanielLongo/cGANs
pointer only; the stored copy get_code serves, from DanielLongo/cGANs, is pointer only (licence: NONE) · get_code("edd684c8d7918d6a")
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.

prepare_results_dir Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
crcrpar/pytorch.sngan_projection/train_64.py
code served (permissive licence) · get_code("71ca378125225f3b")
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) 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 datetime
import json
import os
import tempfile

class Args:
    def __init__(self):
        self.test = False
        self.results_root = tempfile.mkdtemp()
        self.cGAN = False
        self.no_tensorboard = True
        self.num_classes = 10
        self.n_eval_batches = 20
        self.batch_size = 32
        self.eval_batch_size = None
        self.calc_FID = False
        self.n_fid_images = 256
        self.max_iteration = 1000
        self.log_interval = 10
        self.eval_interval = 100
        self.n_fid_batches = None

ARGS = {
    'args': Args()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
tensorboardX — 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
sample_from_data Ran
ran; our contract draft was wrong, not the code
crcrpar/pytorch.sngan_projection/train_64.py
code served (permissive licence) · get_code("d01f1fbb0262694b")
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) 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 argparse

torch.manual_seed(0)

# Create a simple argparse object with cGAN attribute
args = argparse.Namespace(cGAN=True)

# Create a device (CPU only)
device = torch.device('cpu')

# Create a simple data loader as a list of (image, label) tuples
# Images: batch_size=2, channels=3, height=4, width=4
# Labels: batch_size=2 (class indices)
real_images = torch.randn(2, 3, 4, 4)
labels = torch.tensor([0, 1])
data_loader = iter([(real_images, labels)])

ARGS = {
    'args': args,
    'device': device,
    'data_loader': data_loader
}
Setup block drafted by
a language model, Claude Haiku 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 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
str2bool Ran
ran, violated the contract we drafted
XHChen0528/SNGAN_Projection_Pytorch/parameter.py
code served (permissive licence) · get_code("e5b1aff86a339d0e")
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 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.

ARGS = {
    'v': 'True'
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
train_gan Ran
ran on a synthesized input
this paper's copy was not recorded; identical code first harvested from DanielLongo/cGANs
pointer only; the stored copy get_code serves, from DanielLongo/cGANs, is pointer only (licence: NONE) · get_code("2fb479c48e65d7b4")
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.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
str2bool 11 other papers
1 dated earlier, 10 later
1611.01578 (2016-11)
Neural Architecture Search with Reinforcement Learning
1805.11973 (2018-05)
MolGAN: An implicit generative model for small molecular graphs
1806.06029 (2018-06)
One-Shot Unsupervised Cross Domain Translation
and 8 more not named here
adversarial_loss_d 1 other paper
1 dated earlier
1711.10337 (2017-11)
Are GANs Created Equal? A Large-Scale Study
adversarial_loss_g 1 other paper
1 dated earlier
1711.10337 (2017-11)
Are GANs Created Equal? A Large-Scale Study
create_optimizer 1 other paper
1 dated earlier
1605.05396 (2016-05)
Generative Adversarial Text to Image Synthesis
discriminator_loss 1 other paper
1 dated earlier
1605.05396 (2016-05)
Generative Adversarial Text to Image Synthesis
generate_nosie 1 other paper
1 dated earlier
1605.05396 (2016-05)
Generative Adversarial Text to Image Synthesis
train_gan 1 other paper
1 dated earlier
1605.05396 (2016-05)
Generative Adversarial Text to Image Synthesis

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

We propose a novel, projection based way to incorporate the conditional information into the discriminator of GANs that respects the role of the conditional information in the underlining probabilistic model. This approach is in contrast with most frameworks of conditional GANs used in application today, which use the conditional information by concatenating the (embedded) conditional vector to the feature vectors. With this modification, we were able to significantly improve the quality of the class conditional image generation on ILSVRC2012 (ImageNet) 1000-class image dataset from the current state-of-the-art result, and we achieved this with a single pair of a discriminator and a generator. We were also able to extend the application to super-resolution and succeeded in producing highly discriminative super-resolution images. This new structure also enabled high quality category transformation based on parametric functional transformation of conditional batch normalization layers in the generator.

For agents

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

get_harvested_code_for_paper("1802.05637")
get_code_for_paper("1802.05637")
have("1802.05637")

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

curl https://syntology.ai/api/ran/1802.05637.json

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

[![Syntology run record](https://syntology.ai/api/ran/1802.05637.svg)](https://syntology.ai/paper/1802.05637)

Connect an agent — have() is free.