SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1811.09236 · 2018

Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylization

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/1811.09236.json · badge: /api/ran/1811.09236.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
zalandoresearch/famos canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
Archangel212/psgan-batik community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
avgP Ran
ran on a synthesized input
zalandoresearch/famos/utils.py
code served (permissive licence) · get_code("c16b4e4cc0aefbaa")
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 4, dtype family float, shape (2, 4, 1, 1) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# avgP expects a tensor x and applies avg_pool2d with kernel size 16
# avg_pool2d expects a 4D tensor (batch, channels, height, width)
# We need height and width to be at least 16 to apply a 16x16 kernel
# Using batch=2, channels=4, height=20, width=24 for distinct dimensions

x = torch.randn(2, 4, 20, 24)

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 4, dtype family float, shape (2, 4, 1, 1) — shape (2, 4, 1, 1) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
getCanonic Ran
ran on a synthesized input
zalandoresearch/famos/prepareTemplates.py
code served (permissive licence) · get_code("fd39bf43f9a47607")
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 4, dtype family float, shape (1, 4, 5, 2) 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 getCanonic takes parameter x
# It calls x.size() on it, so x must be a tensor
# The affine_grid function expects a grid_size parameter
# Looking at the code: flow = F.affine_grid(theta, x.size())
# theta has shape (1, 2, 3) - batch_size=1, spatial_dims=2, affine_params=3
# x.size() should return a torch.Size that represents the output grid size
# For affine_grid, the output_size typically should be (N, C, H, W) for 2D
# Since theta is (1, 2, 3), we need a 4D size for 2D spatial transformation

x = torch.randn(1, 3, 4, 5)  # batch=1, channels=3, height=4, width=5

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 4, dtype family float, shape (1, 4, 5, 2) — shape (1, 4, 5, 2) 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
smooth_real_labels Ran
ran on a synthesized input
Archangel212/psgan-batik/utils.py
code served (permissive licence) · get_code("6e9690fc4a27a345")
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 random
import math

torch.manual_seed(0)

# Create a small tensor for y parameter
# The function calls y.view(-1) and y.view(y.shape), so we need a valid tensor
y = torch.rand(2, 4)

# The function has two parameters: y and percentage
# percentage has a default value of 0.382
ARGS = {
    "y": y,
    "percentage": 0.382
}
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
wrap Ran
ran on a synthesized input
zalandoresearch/famos/prepareTemplates.py
code served (permissive licence) · get_code("8d113c6800860870")
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 4, dtype family float, shape (1, 4, 3, 2) 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 expects a tensor `f` with shape (1, ?, ?, 2)
# where the last dimension has size 2 (indices 0 and 1 for x and y coordinates)
# It accesses f[0, i, :, 1] and f[0, :, i, 0] and modifies them
# Shape: (batch=1, dim1=4, dim2=3, coordinates=2)

f = torch.randn(1, 4, 3, 2, dtype=torch.float32)

ARGS = {
    "f": f
}
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 4, dtype family float, shape (1, 4, 3, 2) — shape (1, 4, 3, 2) 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
avgG Not yet run
unverified (harvested, no recorded run)
zalandoresearch/famos/utils.py
code served (permissive licence) · get_code("5498af610f852015")
How it ran

no invocation recorded.

calc_gradient_penalty Not yet run
unverified (harvested, no recorded run)
zalandoresearch/famos/network.py
code served (permissive licence) · get_code("f4aa5c2bfe596cdc")
How it ran

no invocation recorded.

reflect_mirror Not yet run
unverified (harvested, no recorded run)
zalandoresearch/famos/prepareTemplates.py
code served (permissive licence) · get_code("9b5ecebf625cc690")
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

Parametric generative deep models are state-of-the-art for photo and non-photo realistic image stylization. However, learning complicated image representations requires compute-intense models parametrized by a huge number of weights, which in turn requires large datasets to make learning successful. Non-parametric exemplar-based generation is a technique that works well to reproduce style from small datasets, but is also compute-intensive. These aspects are a drawback for the practice of digital AI artists: typically one wants to use a small set of stylization images, and needs a fast flexible model in order to experiment with it. With this motivation, our work has these contributions: (i) a novel stylization method called Fully Adversarial Mosaics (FAMOS) that combines the strengths of both parametric and non-parametric approaches; (ii) multiple ablations and image examples that analyze the method and show its capabilities; (iii) source code that will empower artists and machine learning researchers to use and modify FAMOS.

For agents

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

get_harvested_code_for_paper("1811.09236")
get_code_for_paper("1811.09236")
have("1811.09236")

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

curl https://syntology.ai/api/ran/1811.09236.json

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

[![Syntology run record](https://syntology.ai/api/ran/1811.09236.svg)](https://syntology.ai/paper/1811.09236)

Connect an agent — have() is free.