SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.12476 · ICCV · 2021

EigenGAN: Layer-Wise Eigen-Learning for GANs

Meina Kan, Shiguang Shan, Zhenliang He

arXiv · PDF · Open in the Atlas

Code that ran

13 of 16 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, 0 violated it and 0 have no contract verdict; 12 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/2104.12476.json · badge: /api/ran/2104.12476.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
LynnHo/EigenGAN-Tensorflow canonical (classifier label)
classifier basis: census
13 ran · 3 no recorded run
FunctionStatusWhere it lives
directory Ran
ran; our contract draft was wrong, not the code
LynnHo/EigenGAN-Tensorflow/pylib/path.py
code served (permissive licence) · get_code("6151aeafdf1f5100")
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 str. 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 os

def split(path):
    """Return dir, name, ext."""
    dir, name_ext = os.path.split(path)
    name, ext = os.path.splitext(name_ext)
    return (dir, name, ext)

def directory(path):
    return split(path)[0]

# Setup: The function takes a single parameter 'path' which is a string file path.
# We need to provide a valid path string.

ARGS = {
    "path": "/home/user/documents/myfile.txt"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
float2im Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
LynnHo/EigenGAN-Tensorflow/imlib/dtype.py
code served (permissive licence) · get_code("cc45f9ab2e1c2c76")
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, 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 valid input for float2im
# The function expects images to be a numpy array with dtype float32 or float64
# with values in the range [0.0, 1.0]

images = np.array([
    [[0.0, 0.5, 1.0, 0.25],
     [0.75, 0.1, 0.9, 0.5]],
    [[0.2, 0.8, 0.0, 1.0],
     [0.5, 0.5, 0.5, 0.5]]
], dtype=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 3, dtype family float, shape (2, 2, 4) — shape (2, 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
grid_split Ran
ran; our contract draft was wrong, not the code
LynnHo/EigenGAN-Tensorflow/imlib/transform.py
code served (permissive licence) · get_code("e67b1d6de08e88b9")
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
import math

torch.manual_seed(0)

# Create a small image tensor with shape (height, width, channels)
# Using distinct sizes: 6 for height, 8 for width, 3 for channels
image = torch.randn(6, 8, 3)

# Grid cell dimensions
h = 2
w = 3

ARGS = {
    'image': image,
    'h': h,
    'w': w
}
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
immerge Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
LynnHo/EigenGAN-Tensorflow/imlib/transform.py
code served (permissive licence) · get_code("e162886a782f2923")
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, 6, 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 batch of images with distinct dimensions
# Shape: N=2 images, H=4 height, W=3 width, C=3 channels (RGB)
images = np.random.randint(0, 256, size=(2, 4, 3, 3), dtype=np.uint8)

ARGS = {
    "images": images,
    "n_rows": None,
    "n_cols": None,
    "padding": 0,
    "pad_value": 0
}
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, 6, 3) — shape (4, 6, 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
imread Ran
ran, honoured the contract we drafted
LynnHo/EigenGAN-Tensorflow/imlib/basic.py
code served (permissive licence) · get_code("4ccd6f19d65b0289")
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 (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
import tempfile
import os
from PIL import Image

# Create a temporary test image file
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, "test_image.png")

# Create a small test image as uint8
test_image_uint8 = np.random.randint(0, 256, (4, 3), dtype=np.uint8)
Image.fromarray(test_image_uint8).save(temp_image_path)

ARGS = {
    "path": temp_image_path,
    "as_gray": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, skimage — 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 (4, 3) — shape (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
load_json Ran
ran; our contract draft was wrong, not the code
LynnHo/EigenGAN-Tensorflow/pylib/serialization.py
code served (permissive licence) · get_code("be1179109aef84de")
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 dict. 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 json
import tempfile
import os

# Create a temporary JSON file to load
temp_dir = tempfile.mkdtemp()
json_path = os.path.join(temp_dir, "test.json")

# Write a simple JSON file
test_data = {"key": "value", "number": 42, "list": [1, 2, 3]}
with open(json_path, "w") as f:
    json.dump(test_data, f)

# Define arguments for load_json function
ARGS = {
    "path": json_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
load_pickle Ran
ran; our contract draft was wrong, not the code
LynnHo/EigenGAN-Tensorflow/pylib/serialization.py
code served (permissive licence) · get_code("e03dc4ba413aef8e")
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 dict. 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 pickle
import tempfile
import os

# Create a temporary pickle file with some sample data
temp_dir = tempfile.mkdtemp()
temp_path = os.path.join(temp_dir, "test.pkl")

# Create sample data to pickle
sample_data = {
    "key1": [1, 2, 3],
    "key2": "test_string",
    "key3": {"nested": "dict"}
}

# Write the pickle file
with open(temp_path, 'wb') as f:
    pickle.dump(sample_data, f)

# Define arguments for load_pickle
ARGS = {
    "path": temp_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
name Ran
ran; our contract draft was wrong, not the code
LynnHo/EigenGAN-Tensorflow/pylib/path.py
code served (permissive licence) · get_code("0b171043968ae8f3")
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 str. 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 os

# The function 'name' takes a single parameter 'path' (a file path string)
# It calls split(path) which uses os.path.split and os.path.splitext
# These are standard library functions that work with string paths
# No special objects or models needed

ARGS = {
    "path": "/home/user/documents/example.txt"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
run_parallels Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
LynnHo/EigenGAN-Tensorflow/pylib/processing.py
code served (permissive licence) · get_code("c8424809dcc5cbc2")
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 multiprocessing
import torch

torch.manual_seed(0)

def simple_work_fn(x):
    """Simple work function that processes an item."""
    return x * 2

# Create a small iterable to process
iterable = [1, 2, 3, 4, 5]

# Define arguments for run_parallels
ARGS = {
    "work_fn": simple_work_fn,
    "iterable": iterable,
    "max_workers": 2,
    "chunksize": 1,
    "processing_bar": False,
    "backend_executor": multiprocessing.Pool,
    "debug": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — 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
split Ran
ran; our contract draft was wrong, not the code
LynnHo/EigenGAN-Tensorflow/pylib/path.py
code served (permissive licence) · get_code("46efef6d32953519")
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 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 os

# The split function takes a single parameter 'path', which should be a string
# representing a file path. The function uses os.path.split and os.path.splitext
# to decompose the path into directory, filename, and extension components.

ARGS = {
    'path': '/home/user/documents/example.txt'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 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
timeit Ran
ran; our contract draft was wrong, not the code
LynnHo/EigenGAN-Tensorflow/pylib/timer.py
code served (permissive licence) · get_code("a304288e1ef66b2f")
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 function. 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 datetime
import timeit as timeit_module

# Define a simple function to decorate for testing
def sample_function(x, y):
    """A simple function that does some computation."""
    return x + y

# Create ARGS dict with all parameters for the timeit decorator
ARGS = {
    'run_times': 3,
    'fmt': 's',
    'print_at_exit': True,
    'timer': timeit_module.default_timer
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
to_range Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
LynnHo/EigenGAN-Tensorflow/imlib/dtype.py
code served (permissive licence) · get_code("63ddd771c64bd6ba")
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, 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 valid input image array with values in [-1.0, 1.0]
images = np.array([
    [[-0.5, 0.2, -1.0, 0.8],
     [0.3, -0.7, 0.1, -0.9]],
    [[0.0, 0.5, -0.3, 0.7],
     [-0.8, 0.6, 0.2, -0.4]]
], dtype=np.float32)

ARGS = {
    'images': images,
    'min_value': 0.0,
    'max_value': 1.0,
    'dtype': np.float32
}
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, 2, 4) — shape (2, 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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
LynnHo/EigenGAN-Tensorflow/imlib/dtype.py
code served (permissive licence) · get_code("ee49acc532aae040")
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, 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 uint8 image array with values in valid range [0, 255]
images = np.array([
    [[0, 128, 255, 64], [32, 200, 100, 150]],
    [[10, 50, 200, 240], [20, 75, 180, 220]]
], 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, 2, 4) — shape (2, 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
imcrop Not yet run
unverified (harvested, no recorded run)
LynnHo/EigenGAN-Tensorflow/imlib/transform.py
code served (permissive licence) · get_code("c4aaff60bf06e015")
How it ran

no invocation recorded.

load_yaml Not yet run
unverified (harvested, no recorded run)
LynnHo/EigenGAN-Tensorflow/pylib/serialization.py
code served (permissive licence) · get_code("f57b5b6af6b96676")
How it ran

no invocation recorded.

weight_modulation Not yet run
unverified (harvested, no recorded run)
LynnHo/EigenGAN-Tensorflow/tflib/deep_learning/layers_deprecated.py
code served (permissive licence) · get_code("e325e4aec5e56847")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 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, 0 later) and 12 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
directory 2 other papers
2 dated earlier
1312.6114 (2013-12)
Auto-Encoding Variational Bayes
1906.10335 (2019-06)
Perceptual Generative Autoencoders
name 2 other papers
2 dated earlier
1312.6114 (2013-12)
Auto-Encoding Variational Bayes
1906.10335 (2019-06)
Perceptual Generative Autoencoders
split 2 other papers
2 dated earlier
1312.6114 (2013-12)
Auto-Encoding Variational Bayes
1906.10335 (2019-06)
Perceptual Generative Autoencoders
to_range 2 other papers
2 dated earlier
1312.6114 (2013-12)
Auto-Encoding Variational Bayes
1906.10335 (2019-06)
Perceptual Generative Autoencoders

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 studies on Generative Adversarial Network (GAN) reveal that different layers of a generative CNN hold different semantics of the synthesized images. However, few GAN models have explicit dimensions to control the semantic attributes represented in a specific layer. This paper proposes EigenGAN which is able to unsupervisedly mine interpretable and controllable dimensions from different generator layers. Specifically, EigenGAN embeds one linear subspace with orthogonal basis into each generator layer. Via generative adversarial training to learn a target distribution, these layer-wise subspaces automatically discover a set of "eigen-dimensions" at each layer corresponding to a set of semantic attributes or interpretable variations. By traversing the coefficient of a specific eigen-dimension, the generator can produce samples with continuous changes corresponding to a specific semantic attribute. Taking the human face for example, EigenGAN can discover controllable dimensions for high-level concepts such as pose and gender in the subspace of deep layers, as well as low-level concepts such as hue and color in the subspace of shallow layers. Moreover, in the linear case, we theoretically prove that our algorithm derives the principal components as PCA does. Codes can be found in https://github. com/LynnHo/EigenGAN-Tensorflow.

For agents

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

get_harvested_code_for_paper("2104.12476")
get_code_for_paper("2104.12476")
have("2104.12476")

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

curl https://syntology.ai/api/ran/2104.12476.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.12476.svg)](https://syntology.ai/paper/2104.12476)

Connect an agent — have() is free.