Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A project template to simplify building and training deep learning models using Keras.
| Date | Stars |
|---|---|
| 2026-07-31 | 796 |
| 2026-08-05 | 796 |
| 2026-08-06 | 796 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Keras Project Template [](https://www.comet.ml)
A project template to simplify building and training deep learning models using Keras.
# Table of contents
- [Getting Started](#getting-started)
- [Running The Demo Project](#running-the-demo-project)
- [Comet.ml Integration](#cometml-integration)
- [Template Details](#template-details)
- [Project Architecture](#project-architecture)
- [Folder Structure](#folder-structure)
- [Main Components](#main-components)
- [Future Work](#future-work)
- [Example Projects](#example-projects)
- [Contributing](#contributing)
- [Acknowledgements](#acknowledgements)
# Getting Started
This template allows you to simply build and train deep learning models with checkpoints and tensorboard visualization.
In order to use the template you have to:
1. Define a data loader class.
2. Define a model class that inherits from BaseModel.
3. Define a trainer class that inherits.
4. Define a configuration file with the parameters needed in an experiment.
5. Run the model using:
```shell
python main.py -c [path to configuration file]
```
# Running The Demo Project
A simple model for the mnist dataset is available to test the template.
To run the demo project:
1. Start the training using:
```shell
python main.py -c configs/simple_mnist_config.json
```
2. Start Tensorboard visualization using:
```shell
tensorboard --logdir=experiments/simple_mnist/logs
```
<div align="center">
<img align="center" width="600" src="https://github.com/Ahmkel/Keras-Project-Template/blob/master/figures/Tensorboard_demo.PNG?raw=true">
</div>
# Comet.ml Integration
This template also supports reporting to Comet.ml which allows you to see all your hyper-params, metrics, graphs, dependencies and more including real-time metric.
Add your API key [in the configuration file](configs/simple_mnist_config.json#L15):
For example: `"comet_api_key": "your key here"`
Here's how it looks after you start training:
<div align="center">
<img align="center" width="800" src="https://comet-ml.nyc3.digitaloceanspaces.com/CometDemo.gif">
</div>
You can also link your Github repository to your comet.ml project for full version control.
# Template Details
## Project Architecture
<div align="center">
<img align="center" width="600" src="https://github.com/Ahmkel/Keras-Project-Template/blob/master/figures/ProjectArchitecture.jpg?raw=true">
</div>
## Folder Structure
```
├── main.py - here's an example of main that is responsible for the whole pipeline.
│
│
├── base - this folder contains the abstract classes of the project components
│ ├── base_data_loader.py - this file contains the abstract class of the data loader.
│ ├── base_model.py - this file contains the abstract class of the model.
│ └── base_train.py - this file contains the abstract class of the trainer.
│
│
├── model - this folder contains the models of your project.
│ └── simple_mnist_model.py
│
│
├── trainer - this folder contains the trainers of your project.
│ └── simple_mnist_trainer.py
│
|
├── data_loader - this folder contains the data loaders of your project.
│ └── simple_mnist_data_loader.py
│
│
├── configs - this folder contains the experiment and model configs of your project.
│ └── simple_mnist_config.json
│
│
├── datasets - this folder might contain the datasets of your project.
│
│
└── utils - this folder contains any utils you need.
├── config.py - util functions for parsing the config files.
├── dirs.py - util functions for creating directories.
└── utils.py - util functions for parsing arguments.
```
## Main Components
### Models
You need to:
1. Create a model class that inherits from **BaseModel**.
2. Override the ***build_model*** function which defines your model.
3. Call ***build_model*** function from the constructoExcerpt of 7,134 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9f31ff41f8f61e13, llm:description: 'A project template to simplify building and training deep learning models using Keras.' (repository description)
matched fp:9f31ff41f8f61e13, llm:description: 'A project template to simplify building and training deep learning models using Keras.' (repository description)
