Package: RGAN 0.1.1
Marcel Neunhoeffer
RGAN: Generative Adversarial Nets (GAN) in R
An easy way to get started with Generative Adversarial Nets (GAN) in R. The GAN algorithm was initially described by Goodfellow et al. 2014 <https://proceedings.neurips.cc/paper/2014/file/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf>. A GAN can be used to learn the joint distribution of complex data by comparison. A GAN consists of two neural networks a Generator and a Discriminator, where the two neural networks play an adversarial minimax game. Built-in GAN models make the training of GANs in R possible in one line and make it easy to experiment with different design choices (e.g. different network architectures, value functions, optimizers). The built-in GAN models work with tabular data (e.g. to produce synthetic data) and image data. Methods to post-process the output of GAN models to enhance the quality of samples are available.
Authors:
RGAN_0.1.1.tar.gz
RGAN_0.1.1.zip(r-4.5)RGAN_0.1.1.zip(r-4.4)RGAN_0.1.1.zip(r-4.3)
RGAN_0.1.1.tgz(r-4.4-any)RGAN_0.1.1.tgz(r-4.3-any)
RGAN_0.1.1.tar.gz(r-4.5-noble)RGAN_0.1.1.tar.gz(r-4.4-noble)
RGAN_0.1.1.tgz(r-4.4-emscripten)RGAN_0.1.1.tgz(r-4.3-emscripten)
RGAN.pdf |RGAN.html✨
RGAN/json (API)
NEWS
| # Install 'RGAN' in R: |
| install.packages('RGAN', repos = c('https://mneunhoe.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/mneunhoe/rgan/issues
Last updated 1 years agofrom:1b6d0f319f. Checks:ERROR: 1 WARNING: 6. Indexed: yes.
| Target | Result | Date |
|---|---|---|
| Doc / Vignettes | FAIL | Sep 10 2024 |
| R-4.5-win | WARNING | Sep 10 2024 |
| R-4.5-linux | WARNING | Sep 10 2024 |
| R-4.4-win | WARNING | Sep 10 2024 |
| R-4.4-mac | WARNING | Sep 10 2024 |
| R-4.3-win | WARNING | Sep 10 2024 |
| R-4.3-mac | WARNING | Sep 10 2024 |
Exports:data_transformerDCGAN_DiscriminatorDCGAN_GeneratorDiscriminatorexpert_sample_synthetic_datagan_trainerGAN_update_plotGAN_update_plot_imagegan_update_stepGAN_value_fctGeneratorKLWGAN_value_fctsample_synthetic_datasample_toydatatorch_rand_abWGAN_value_fctWGAN_weight_clipper
Dependencies:bitbit64callrclicolorspacecorodescellipsisfansifarverggplot2gluegridExtragtableisobandjsonlitelabelinglatticelifecyclemagrittrMASSMatrixmgcvmunsellnlmepillarpkgconfigprocessxpsR6RColorBrewerRcpprlangsafetensorsscalestibbletorchutf8vctrsviridisviridisLitewithr
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Data Transformer | data_transformer |
| DCGAN Discriminator | DCGAN_Discriminator |
| DCGAN Generator | DCGAN_Generator |
| Discriminator | Discriminator |
| Sample Synthetic Data with explicit noise input | expert_sample_synthetic_data |
| gan_trainer | gan_trainer |
| GAN_update_plot | GAN_update_plot |
| GAN_update_plot_image | GAN_update_plot_image |
| gan_update_step | gan_update_step |
| GAN Value Function | GAN_value_fct |
| Generator | Generator |
| KL WGAN loss on fake examples | kl_fake |
| KL WGAN loss for Generator training | kl_gen |
| KL WGAN loss on real examples | kl_real |
| KLWGAN Value Function | KLWGAN_value_fct |
| Sample Synthetic Data from a trained RGAN | sample_synthetic_data |
| Sample Toydata | sample_toydata |
| Uniform Random numbers between values a and b | torch_rand_ab |
| WGAN Value Function | WGAN_value_fct |
| WGAN Weight Clipper | WGAN_weight_clipper |