SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.03828 · 2020

Attentive Normalization for Conditional Image Generation

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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 3 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/2004.03828.json · badge: /api/ran/2004.03828.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
shepnerd/AttenNorm community (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
FunctionStatusWhere it lives
f2uint Ran
ran on a synthesized input
shepnerd/AttenNorm/inpaint-attnorm/util/util.py
code served (permissive licence) · get_code("e6bbab52d3ddea75")
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 int, 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
import tensorflow as tf

# Test case 1: numpy array input
numpy_array = np.array([[-0.5, 0.0, 0.5, 1.0], [0.25, -0.75, 0.1, -0.9]])

# Test case 2: tensorflow tensor input
tf_tensor = tf.constant([[-0.5, 0.0, 0.5, 1.0], [0.25, -0.75, 0.1, -0.9]], dtype=tf.float32)

ARGS = {
    "x": numpy_array
}
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 ndarray, ndim 2, dtype family int, 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
gauss_kernel Ran
ran on a synthesized input
shepnerd/AttenNorm/inpaint-attnorm/net/ops.py
code served (permissive licence) · get_code("c5bc38ee9334ced5")
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 4, dtype family float, shape (21, 21, 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 numpy as np
import scipy.stats as st

# The function takes two optional parameters: size and sigma
# Both have default values, so we need to provide valid arguments

ARGS = {
    "size": 21,
    "sigma": 3
}
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 4, dtype family float, shape (21, 21, 1, 1) — shape (21, 21, 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
generate_mask_rect Ran
ran on a synthesized input
shepnerd/AttenNorm/inpaint-attnorm/util/util.py
code served (permissive licence) · get_code("b1331905adc5865e")
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 3, dtype family float, shape (8, 6, 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 numpy as np

np.random.seed(0)

ARGS = {
    "im_shapes": (8, 6),
    "mask_shapes": (4, 3),
    "rand": True
}
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 ndarray, ndim 3, dtype family float, shape (8, 6, 1) — shape (8, 6, 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
att_normalization Not yet run
unverified (harvested, no recorded run)
shepnerd/AttenNorm/inpaint-attnorm/net/network.py
code served (permissive licence) · get_code("9ea537af23b53405")
How it ran

no invocation recorded.

free_form_mask_tf Not yet run
unverified (harvested, no recorded run)
shepnerd/AttenNorm/inpaint-attnorm/net/ops.py
code served (permissive licence) · get_code("d335908a6881e089")
How it ran

no invocation recorded.

np_free_form_mask Not yet run
unverified (harvested, no recorded run)
shepnerd/AttenNorm/inpaint-attnorm/net/ops.py
code served (permissive licence) · get_code("0c044ee49bfaec49")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 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
np_free_form_mask 2 other papers
1 dated earlier, 1 later
1810.08771 (2018-10)
Image Inpainting via Generative Multi-column Convolutional Neural Networks
2008.03737 (2020-08)
Recurrent Feature Reasoning for Image Inpainting
f2uint 1 other paper
1 dated earlier
1810.08771 (2018-10)
Image Inpainting via Generative Multi-column Convolutional Neural Networks
gauss_kernel 1 other paper
1 dated earlier
1810.08771 (2018-10)
Image Inpainting via Generative Multi-column Convolutional Neural Networks
generate_mask_rect 1 other paper
1 dated earlier
1810.08771 (2018-10)
Image Inpainting via Generative Multi-column Convolutional Neural Networks

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

Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain. It is still not sufficient for categories with complicated structures. In this paper, we characterize long-range dependence with attentive normalization (AN), which is an extension to traditional instance normalization. Specifically, the input feature map is softly divided into several regions based on its internal semantic similarity, which are respectively normalized. It enhances consistency between distant regions with semantic correspondence. Compared with self-attention GAN, our attentive normalization does not need to measure the correlation of all locations, and thus can be directly applied to large-size feature maps without much computational burden. Extensive experiments on class-conditional image generation and semantic inpainting verify the efficacy of our proposed module.

For agents

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

get_harvested_code_for_paper("2004.03828")
get_code_for_paper("2004.03828")
have("2004.03828")

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

curl https://syntology.ai/api/ran/2004.03828.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.03828.svg)](https://syntology.ai/paper/2004.03828)

Connect an agent — have() is free.