Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/sarus-tech/tf2-published-models
Sarus implementation of classical ML models. The models are implemented using the Keras API of tensorflow 2. Vizualization are implemented and can be seen in tensorboard.
https://github.com/sarus-tech/tf2-published-models
ai generative-model keras tensorflow tensorflow2
Last synced: 3 months ago
JSON representation
Sarus implementation of classical ML models. The models are implemented using the Keras API of tensorflow 2. Vizualization are implemented and can be seen in tensorboard.
- Host: GitHub
- URL: https://github.com/sarus-tech/tf2-published-models
- Owner: sarus-tech
- License: apache-2.0
- Created: 2020-07-06T14:20:41.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2021-09-23T07:51:25.000Z (over 3 years ago)
- Last Synced: 2024-08-01T03:16:25.734Z (6 months ago)
- Topics: ai, generative-model, keras, tensorflow, tensorflow2
- Language: Python
- Homepage: https://sarus.tech/
- Size: 677 KB
- Stars: 38
- Watchers: 6
- Forks: 5
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-tensorflow-2 - Sarus TF2 Models - A long list of recent generative models implemented in clean, easy to reuse, Tensorflow 2 code (Plain Autoencoder, VAE, VQ-VAE, PixelCNN, Gated PixelCNN, PixelCNN++, PixelSNAIL, Conditional Neural Processes). (Sample Codes / Projects <a name="sample" /> ⛏️📐📁 / General 🚧 <a name="GeneralCode" />)
- awesome-tensorflow - Sarus TF2 Models - A long list of recent generative models implemented in clean, easy to reuse, Tensorflow 2 code (Plain Autoencoder, VAE, VQ-VAE, PixelCNN, Gated PixelCNN, PixelCNN++, PixelSNAIL, Conditional Neural Processes). (Models/Projects)
- fucking-awesome-tensorflow - Sarus TF2 Models - A long list of recent generative models implemented in clean, easy to reuse, Tensorflow 2 code (Plain Autoencoder, VAE, VQ-VAE, PixelCNN, Gated PixelCNN, PixelCNN++, PixelSNAIL, Conditional Neural Processes). (Models/Projects)
README
# Sarus published models
Sarus implementation of classical ML models. The models are implemented using the Keras API of tensorflow 2. Vizualization are implemented and can be seen in tensorboard.
The required packages are managed with `pipenv` and can be installed using `pipenv install`. Please see the [pipenv documentation](https://pipenv-fork.readthedocs.io/en/latest/) for more information.
## Philosophy
These models' implementations are intended to be easy to read and to adapt by making use of the latest Tensorflow 2 library and Keras API.
## Basic usage
To install and train a model.
```shell
pipenv install
pipenv shell
python train.py
```To visualize losses and reconstructions.
```shell
tensorboard --logdir ./logs/
```## Available models
* [Simple Autoencoder](./simple_autoencoder)
* [Variational Autoencoder (VAE)](./vae)
* [Vector Quantized Autoencoder (VQ-VAE)](./vqvae)
* [PixelCNN](./pixelcnn)
* [Gated PixelCNN](./gated_pixelcnn)
* [PixelCNN++](./pixelcnn_plus)
* [Conditional Neural Processes](./cnp)
* [PixelSNAIL](./pixelsnail)