Are GANs Created Equal? A Large-Scale Study
Authors: Mario Lucic, Karol Kurach, Marcin Michalski, Sylvain Gelly, Olivier Bousquet
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct a neutral, multi-faceted large-scale empirical study on state-of-the art models and evaluation measures. |
| Researcher Affiliation | Industry | Mario Lucic Karol Kurach Marcin Michalski Google Brain Olivier Bousquet Sylvain Gelly; Correspondence to {lucic,kkurach}@google.com. |
| Pseudocode | No | The paper describes methods in prose and equations but does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | We open-sourced our experimental setup and model implementations at goo.gl/G8kf5J. |
| Open Datasets | Yes | We evaluate the bias and variance of FID on four data sets from the GAN literature. ... These data sets are a popular choice for generative modeling, range from simple to medium complexity, which makes it possible to run many experiments as well as getting decent results. |
| Dataset Splits | Yes | We start by using the default train vs. test partition and compute the FID between the test set (limited to N = 10000 samples for Celeb A) and a sample of size N from the train set. ... To choose the best model, every 5 epochs we compute the FID between the 10k samples generated by the model and the 10k samples from the test set. |
| Hardware Specification | Yes | Reproducing these experiments requires approximately 6.85 GPU years (NVIDIA P100). |
| Software Dependencies | No | The paper mentions using "Adam" as the optimization algorithm but does not specify version numbers for any key software components or libraries. |
| Experiment Setup | Yes | For all experiments we fix the latent code size to 64 and the prior distribution over the latent space to be uniform on [ 1, 1]64, except for VAE where it is Gaussian N(0, I). We choose Adam [13] as the optimization algorithm... We apply the same learning rate for both generator and discriminator. We set the batch size to 64 and perform optimization for 20 epochs on MNIST and FASHION MNIST, 40 on CELEBA and 100 on CIFAR. ... We report the hyperparameter ranges and other details in Appendix A. |