SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.09479 · 2022

StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 11 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
POSTECH-CVLab/PyTorch-StudioGAN canonical 1 of 1
lyqcom/biggan pwc_unofficial 5 of 10
FunctionStatusWhere it lives
D_arch Ran lyqcom/biggan/model/BigGAN.py
code served (permissive licence) · get_code("85eb95cce203dfc7")
cal_fid Ran lyqcom/biggan/src/inception_utils.py
code served (permissive licence) · get_code("d441601e14f2c498")
find_classes Ran lyqcom/biggan/src/datasets.py
code served (permissive licence) · get_code("130fb10627e87139")
is_image_file Ran lyqcom/biggan/src/datasets.py
code served (permissive licence) · get_code("39565434228935b8")
make_dataset Ran lyqcom/biggan/src/datasets.py
code served (permissive licence) · get_code("c92e605aa8f6c735")
normalize_2nd_moment Ran POSTECH-CVLab/PyTorch-StudioGAN/src/models/stylegan2.py
pointer only (licence: NOASSERTION) · get_code("670fe68b890c9792")
CAL_FID Not yet run lyqcom/biggan/src/inception_utils.py
code served (permissive licence) · get_code("645f242bb645d145")
G_arch Not yet run lyqcom/biggan/model/BigGAN.py
code served (permissive licence) · get_code("44d6a6343f6eb182")
add_sample_parser Not yet run lyqcom/biggan/src/utils.py
code served (permissive licence) · get_code("c4171e8c1ba5ea65")
numpy_calculate_frechet_distance Not yet run lyqcom/biggan/src/inception_utils.py
code served (permissive licence) · get_code("69b2abc7f7010394")
update_config_roots Not yet run lyqcom/biggan/src/utils.py
code served (permissive licence) · get_code("e6f2eaa40b13c353")

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 Network (GAN) is one of the state-of-the-art generative models for realistic image synthesis. While training and evaluating GAN becomes increasingly important, the current GAN research ecosystem does not provide reliable benchmarks for which the evaluation is conducted consistently and fairly. Furthermore, because there are few validated GAN implementations, researchers devote considerable time to reproducing baselines. We study the taxonomy of GAN approaches and present a new open-source library named StudioGAN. StudioGAN supports 7 GAN architectures, 9 conditioning methods, 4 adversarial losses, 12 regularization modules, 3 differentiable augmentations, 7 evaluation metrics, and 5 evaluation backbones. With our training and evaluation protocol, we present a large-scale benchmark using various datasets (CIFAR10, ImageNet, AFHQv2, FFHQ, and Baby/Papa/Granpa-ImageNet) and 3 different evaluation backbones (InceptionV3, SwAV, and Swin Transformer). Unlike other benchmarks used in the GAN community, we train representative GANs, including BigGAN and StyleGAN series in a unified training pipeline and quantify generation performance with 7 evaluation metrics. The benchmark evaluates other cutting-edge generative models (e.g., StyleGAN-XL, ADM, MaskGIT, and RQ-Transformer). StudioGAN provides GAN implementations, training, and evaluation scripts with the pre-trained weights. StudioGAN is available at https://github.com/POSTECH-CVLab/PyTorch-StudioGAN.

For agents

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

get_harvested_code_for_paper("2206.09479")
get_code_for_paper("2206.09479")
have("2206.09479")

Connect an agent — have() is free.