{ "id": 303431, "title": "SOTA GANs in fewest lines of code", "url": "/competitions/gan-getting-started/discussion/303431", "author_name": "", "post_date": "2022-01-27T15:32:02.151920Z", "votes": 8, "comment_count": 1, "views": 0, "content": "

pyradox-generative is a python library provides light weight trainers for the following generative models in TensorFlow2

\n
    \n
  1. Vanilla/ Deep Convolutional GAN:
    2. \n
  2. Conditional GAN:
    3. \n
  3. Wasserstein GAN
    4. \n
  4. Variational Auto Encoder:
    5. \n
  5. Style GAN:
    6. \n
  6. Cycle GAN
    7. \n
\n

If you find my work interesting, please do upvote the notebooks or star the repo

", "messages": [ { "id": "1666238", "postDate": "01/27/2022 15:32:02", "content": "

pyradox-generative is a python library provides light weight trainers for the following generative models in TensorFlow2

\n
    \n
  1. Vanilla/ Deep Convolutional GAN:
    2. \n
  2. Conditional GAN:
    3. \n
  3. Wasserstein GAN
    4. \n
  4. Variational Auto Encoder:
    5. \n
  5. Style GAN:
    6. \n
  6. Cycle GAN
    7. \n
\n

If you find my work interesting, please do upvote the notebooks or star the repo

", "rawMarkdown": "[pyradox-generative](https://github.com/Ritvik19/pyradox-generative) is a python library provides light weight trainers for the following generative models in TensorFlow2\n1. Vanilla/ Deep Convolutional GAN:\n * Vanilla GAN Paper: [Generative Adversarial Networks](https://arxiv.org/abs/1406.2661)\n * Deep Convolutional GAN Paper: [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://arxiv.org/abs/1511.06434)\n * [DC-GAN implementation on MNIST](https://www.kaggle.com/ritvik1909/deep-convolutional-gan)\n2. Conditional GAN:\n * Original Paper: [Conditional Generative Adversarial Nets](https://arxiv.org/abs/1411.1784)\n * [Implementation on MNIST](https://www.kaggle.com/ritvik1909/conditional-gan)\n3. Wasserstein GAN\n * W-GAN Paper: [Wasserstein GAN](https://arxiv.org/abs/1701.07875)\n * W-GAN GP Paper: [Improved Training of Wasserstein GANs](https://arxiv.org/abs/1704.00028)\n * [Implementation on MNIST](https://www.kaggle.com/ritvik1909/wasserstein-gan-with-gradient-penalty)\n4. Variational Auto Encoder:\n * Paper: [An Introduction to Variational Autoencoders](https://arxiv.org/abs/1906.02691)\n * [Implementation on MNIST](https://www.kaggle.com/ritvik1909/variational-auto-encoder)\n5. Style GAN:\n * Paper: [A Style-Based Generator Architecture for Generative Adversarial Networks](https://arxiv.org/abs/1812.04948)\n * [Implementation on MNIST](https://www.kaggle.com/ritvik1909/style-gan)\n6. Cycle GAN\n * Paper: [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks\n](v)\n * [Implementation on horse-zebra dataset](https://www.kaggle.com/ritvik1909/cycle-gan)\n\nIf you find my work interesting, please do upvote the notebooks or star the repo", "votes": null }, { "id": "1666464", "postDate": "01/27/2022 19:05:59", "content": "

Thank you Ritvik Rastogi, for sharing the pyradox-generative python library with informative links.

\n

You are doing good job. Keep it continue.

", "rawMarkdown": "#### Thank you **[Ritvik Rastogi](@ritvik1909)**, for sharing the ***pyradox-generative*** **python library** with informative links. \n#### You are doing good job. Keep it continue.", "votes": null } ], "comments": [ { "id": 1666464, "author_name": "imuhammadismail", "author_url": "", "post_date": "01/27/2022 19:05:59", "content": "

Thank you Ritvik Rastogi, for sharing the pyradox-generative python library with informative links.

\n

You are doing good job. Keep it continue.

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1666238": "[pyradox-generative](https://github.com/Ritvik19/pyradox-generative) is a python library provides light weight trainers for the following generative models in TensorFlow2\n1. Vanilla/ Deep Convolutional GAN:\n * Vanilla GAN Paper: [Generative Adversarial Networks](https://arxiv.org/abs/1406.2661)\n * Deep Convolutional GAN Paper: [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://arxiv.org/abs/1511.06434)\n * [DC-GAN implementation on MNIST](https://www.kaggle.com/ritvik1909/deep-convolutional-gan)\n2. Conditional GAN:\n * Original Paper: [Conditional Generative Adversarial Nets](https://arxiv.org/abs/1411.1784)\n * [Implementation on MNIST](https://www.kaggle.com/ritvik1909/conditional-gan)\n3. Wasserstein GAN\n * W-GAN Paper: [Wasserstein GAN](https://arxiv.org/abs/1701.07875)\n * W-GAN GP Paper: [Improved Training of Wasserstein GANs](https://arxiv.org/abs/1704.00028)\n * [Implementation on MNIST](https://www.kaggle.com/ritvik1909/wasserstein-gan-with-gradient-penalty)\n4. Variational Auto Encoder:\n * Paper: [An Introduction to Variational Autoencoders](https://arxiv.org/abs/1906.02691)\n * [Implementation on MNIST](https://www.kaggle.com/ritvik1909/variational-auto-encoder)\n5. Style GAN:\n * Paper: [A Style-Based Generator Architecture for Generative Adversarial Networks](https://arxiv.org/abs/1812.04948)\n * [Implementation on MNIST](https://www.kaggle.com/ritvik1909/style-gan)\n6. Cycle GAN\n * Paper: [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks\n](v)\n * [Implementation on horse-zebra dataset](https://www.kaggle.com/ritvik1909/cycle-gan)\n\nIf you find my work interesting, please do upvote the notebooks or star the repo", "1666464": "#### Thank you **[Ritvik Rastogi](@ritvik1909)**, for sharing the ***pyradox-generative*** **python library** with informative links. \n#### You are doing good job. Keep it continue." }, "source": "meta" }