SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1611.06355 · 2016

Invertible Conditional GANs for image editing

arXiv · PDF · Open in the Atlas

Code that ran

7 of 18 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 7 have no contract verdict; 0 failures of our instrument; 11 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/1611.06355.json · badge: /api/ran/1611.06355.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
nguyenquangduc2000/AttGAN community (classifier label)
classifier basis not recorded on the link
7 ran · 11 no recorded run
FunctionStatusWhere it lives
float2im Ran
ran on a synthesized input
nguyenquangduc2000/AttGAN/imlib/dtype.py
code served (permissive licence) · get_code("4f277a0259d52125")
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

# Create a small float32 array in the range [0, 1.0]
images = np.random.rand(2, 4).astype(np.float32)

ARGS = {
    'images': images
}
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 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
gray2rgb Ran
ran on a synthesized input
nguyenquangduc2000/AttGAN/imlib/transform.py
code served (permissive licence) · get_code("63a3d304071b7858")
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 int, shape (4, 5, 3) 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

# Create a 2D grayscale image (single image)
gray_2d = np.random.randint(0, 256, size=(4, 5), dtype=np.uint8)

ARGS = {
    "images": gray_2d
}
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 int, shape (4, 5, 3) — shape (4, 5, 3) 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
rgb2gray Ran
ran on a synthesized input
nguyenquangduc2000/AttGAN/imlib/transform.py
code served (permissive licence) · get_code("fe032a1a678b491f")
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 int, shape (2, 4, 3) 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

# Create a small RGB image batch: shape (batch=2, height=4, width=3, channels=3)
images_4d = np.random.randint(0, 256, size=(2, 4, 3, 3), dtype=np.uint8)

ARGS = {
    "images": images_4d
}
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 int, shape (2, 4, 3) — shape (2, 4, 3) 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
shape Ran
ran on a synthesized input
nguyenquangduc2000/AttGAN/tflib/utils.py
code served (permissive licence) · get_code("554e9812968047de")
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 1, dtype family int; 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

# Create a mock tensor that has a get_shape() method returning a TensorShape
# The function calls .get_shape().as_list() on the tensor parameter
mock_tensor = tf.constant([[1.0, 2.0, 3.0, 4.0],
                           [5.0, 6.0, 7.0, 8.0]])

ARGS = {
    "tensor": mock_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — 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
tensors_filter Ran
ran on a synthesized input
nguyenquangduc2000/AttGAN/tflib/variable.py
code served (permissive licence) · get_code("749502aa266817bc")
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 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

# Create a small stand-in tensor class with a 'name' attribute
class NamedTensor:
    def __init__(self, name):
        self.name = name

# Construct tensors with distinct names for filtering
tensors = [
    NamedTensor("conv_layer_weights"),
    NamedTensor("conv_layer_bias"),
    NamedTensor("linear_layer_weights"),
    NamedTensor("linear_layer_bias"),
    NamedTensor("batch_norm_scale"),
]

# Test with different filter scenarios
filters_single = "conv_layer"
filters_multiple = ["conv_layer", "batch_norm"]

combine_type = 'or'

ARGS = {
    'tensors': tensors,
    'filters': filters_single,
    'combine_type': combine_type,
}
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, ndim 1, 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
to_range Ran
ran on a synthesized input
nguyenquangduc2000/AttGAN/imlib/dtype.py
code served (permissive licence) · get_code("06abdda251d33eb6")
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

# Create valid test images in the range [-1.0, 1.0]
images = np.array([
    [-1.0, -0.5, 0.0, 0.5],
    [1.0, 0.25, -0.75, 0.1]
], dtype=np.float32)

ARGS = {
    "images": images,
    "min_value": 0.0,
    "max_value": 1.0,
    "dtype": None
}
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 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
uint2im Ran
ran on a synthesized input
nguyenquangduc2000/AttGAN/imlib/dtype.py
code served (permissive licence) · get_code("8d6a574072fa743d")
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 (2, 4, 3) 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

# Create uint8 images with shape (2, 4, 3) - batch of 2, height 4, width 3
images = np.random.randint(0, 256, size=(2, 4, 3), dtype=np.uint8)

ARGS = {
    'images': images
}
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 (2, 4, 3) — shape (2, 4, 3) 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
batch_dataset Not yet run
unverified (harvested, no recorded run)
nguyenquangduc2000/AttGAN/data.py
code served (permissive licence) · get_code("d74a019e9b0320c6")
How it ran

no invocation recorded.

disk_image_batch_dataset Not yet run
unverified (harvested, no recorded run)
nguyenquangduc2000/AttGAN/data.py
code served (permissive licence) · get_code("d8762221161a8ab0")
How it ran

no invocation recorded.

global_variables Not yet run
unverified (harvested, no recorded run)
nguyenquangduc2000/AttGAN/tflib/variable.py
code served (permissive licence) · get_code("55672872b27f268a")
How it ran

no invocation recorded.

imdecode Not yet run
unverified (harvested, no recorded run)
nguyenquangduc2000/AttGAN/imlib/encode.py
code served (permissive licence) · get_code("a156a0a0c281bb37")
How it ran

no invocation recorded.

imencode Not yet run
unverified (harvested, no recorded run)
nguyenquangduc2000/AttGAN/imlib/encode.py
code served (permissive licence) · get_code("bf6d096b9db2c499")
How it ran

no invocation recorded.

imread Not yet run
unverified (harvested, no recorded run)
nguyenquangduc2000/AttGAN/imlib/basic.py
code served (permissive licence) · get_code("b50105e0a61b2c28")
How it ran

no invocation recorded.

imresize Not yet run
unverified (harvested, no recorded run)
nguyenquangduc2000/AttGAN/imlib/transform.py
code served (permissive licence) · get_code("bc12329c875db868")
How it ran

no invocation recorded.

imwrite Not yet run
unverified (harvested, no recorded run)
nguyenquangduc2000/AttGAN/imlib/basic.py
code served (permissive licence) · get_code("a7aec6c9071c5edd")
How it ran

no invocation recorded.

session Not yet run
unverified (harvested, no recorded run)
nguyenquangduc2000/AttGAN/tflib/utils.py
code served (permissive licence) · get_code("5aaee13c67987c61")
How it ran

no invocation recorded.

summary Not yet run
unverified (harvested, no recorded run)
nguyenquangduc2000/AttGAN/tflib/utils.py
code served (permissive licence) · get_code("c97c0ccc10798ca5")
How it ran

no invocation recorded.

trainable_variables Not yet run
unverified (harvested, no recorded run)
nguyenquangduc2000/AttGAN/tflib/variable.py
code served (permissive licence) · get_code("58fd13674efd98c4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 17 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 14 later) and 1 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
session 2 other papers
1 dated earlier, 1 later
1312.6114 (2013-12)
Auto-Encoding Variational Bayes
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
shape 2 other papers
1 dated earlier, 1 later
1312.6114 (2013-12)
Auto-Encoding Variational Bayes
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
summary 2 other papers
1 dated earlier, 1 later
1312.6114 (2013-12)
Auto-Encoding Variational Bayes
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
disk_image_batch_dataset 1 other paper
1 later
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
float2im 1 other paper
1 later
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
global_variables 1 other paper
1 dated earlier
1312.6114 (2013-12)
Auto-Encoding Variational Bayes
gray2rgb 1 other paper
1 later
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
imdecode 1 other paper
1 later
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
imencode 1 other paper
1 later
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
imread 1 other paper
1 later
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
imresize 1 other paper
1 later
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
imwrite 1 other paper
1 later
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
rgb2gray 1 other paper
1 later
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
tensors_filter 1 other paper
1 dated earlier
1312.6114 (2013-12)
Auto-Encoding Variational Bayes
to_range 1 other paper
1 later
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
trainable_variables 1 other paper
1 dated earlier
1312.6114 (2013-12)
Auto-Encoding Variational Bayes
uint2im 1 other paper
1 later
1904.09709 (2019-04)
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing

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

Generative Adversarial Networks (GANs) have recently demonstrated to successfully approximate complex data distributions. A relevant extension of this model is conditional GANs (cGANs), where the introduction of external information allows to determine specific representations of the generated images. In this work, we evaluate encoders to inverse the mapping of a cGAN, i.e., mapping a real image into a latent space and a conditional representation. This allows, for example, to reconstruct and modify real images of faces conditioning on arbitrary attributes. Additionally, we evaluate the design of cGANs. The combination of an encoder with a cGAN, which we call Invertible cGAN (IcGAN), enables to re-generate real images with deterministic complex modifications.

For agents

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

get_harvested_code_for_paper("1611.06355")
get_code_for_paper("1611.06355")
have("1611.06355")

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

curl https://syntology.ai/api/ran/1611.06355.json

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

[![Syntology run record](https://syntology.ai/api/ran/1611.06355.svg)](https://syntology.ai/paper/1611.06355)

Connect an agent — have() is free.