Skip to content

Commit

Permalink
feat (documentation): added get started part and linked rerun-animati…
Browse files Browse the repository at this point in the history
…on to the corresponding page + minor updates
  • Loading branch information
spthermo committed Sep 17, 2024
1 parent 740f553 commit f3714ce
Show file tree
Hide file tree
Showing 5 changed files with 36 additions and 42 deletions.
2 changes: 1 addition & 1 deletion docs/content/about/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ toc: false
**GANIMATEER** proposes the design and implementation of an AI-based post-processing toolset for automating the character animation process, widening the spectrum of its potential users. To achieve this goal, [Moverse](https://moverse.ai/) will leverage the in-house suite of AI-based character animation editing services to ultimately form a guided inversion toolset that will deliver realistic character animations based on user input. The toolset will be offered for experimentation to the EMIL consortium.

## Team
Our team comprises scientists and engineers with overlapping and complementary expertise and experiences:
We are a team of computer engineers with complementary expertise in the intersection of computer vision, machine learning and graphics:

<!-- - [Nikolaos Zioulis](https://zokin.github.io/)
- [Spyridon Thermos](https://spthermo.github.io/)
Expand Down
8 changes: 2 additions & 6 deletions docs/content/docs/_index.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,14 +7,10 @@ title: Introduction

<!--more-->

## What is GANIMATEER?

GANIMATEER is `...`

## Features

- **Feature1** - asdf
- **Feature2** - asdf
- **Feature1** - Generate variations of a single input 3D animation.
- **Feature2** - Visualize any 3D animation using a flexible plugin.

## Questions or Feedback?

Expand Down
2 changes: 1 addition & 1 deletion docs/content/docs/ganimator/_index.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
title: GANimator
weight: 2
prev: /docs/getting-started
prev: /docs/
next: /docs/ganimator/data_preprocess
sidebar:
open: true
Expand Down
59 changes: 27 additions & 32 deletions docs/content/docs/getting-started.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,61 +7,56 @@ prev: /docs

## Quick Start / Overview

{{< icon "github" >}}&nbsp;[moverseai/ganimateer/ganimator](https://www.github.com/moverseai/ganimateer/ganimator)
{{< icon "github" >}}&nbsp;[moverseai/moai](https://www.github.com/moverseai/moai)

<img src="https://docs.github.com/assets/cb-77734/mw-1440/images/help/repository/use-this-template-button.webp" width="500">
<!-- <img src="https://docs.github.com/assets/cb-77734/mw-1440/images/help/repository/use-this-template-button.webp" width="500">
[🌐 Demo ↗](https://moverseai.github.io/single-shot/)
[🌐 Demo ↗](https://moverseai.github.io/single-shot/) -->

`moai` is a PyTorch-based AI Model Development Kit (MDK) that aims to improve data-driven model workflows, design and understanding

## Start as New Project

#### Steps

{{% steps %}}

### first step
### Prerequisites
The following python packages are required for using the supported features and the underlying model development kit:

```shell
moai run ... --param=yaml
```
- Python 3.10
- PyTorch 2.2.0 (cuda version)
- Cuda 11.4

### second step
### Install `moai`
Clone the master branch from `moai` [repository](https://github.com/moverseai/moai/) and install it by opening a command line on the source directory and running:

```shell
# train
moai run ...
pip install -e .
```

```yaml
model:
config:
- something: 1
```
### third step
...
The resulting `...`

{{% /steps %}}
### Validate `moai` installation
To validate that the `moai` mdk has been successfully installed and there is no dependency missing, run the following `MNIST` example from the (outer) `moai` directory:

Train a simple multi-layer perceptron (MLP) using the `MNIST` data:

{{% details title="How to ?" %}}

To `...`
```shell
# train
python -m moai run fit moai/conf/examples/MNIST/main.yaml +DATA_ROOT=path/to/download/and/save/MNIST
```

Test the trained by loading its checkpoint:
```shell
cmd line
# test
python -m moai run test moai/conf/examples/MNIST/main.yaml +DATA_ROOT=path/to/download/and/save/MNIST +CKPT=path/to/trained/model/checkpoint
```

{{% /details %}}
{{% /steps %}}

## Next

Explore the following sections to start adding more contents:
Note that `moai` operates as the backbone of the developed tools and plugins, which can be explored in the following sections:

{{< cards >}}
{{< card link="../ganimator/configuration" title="GANimator" icon="document-duplicate" >}}
{{< card link="../rerun_animation/configuration" title="Rerun Animation" icon="adjustments" >}}
{{< card link="../ganimator/" title="GANimator" icon="document-duplicate" >}}
{{< card link="../rerun_animation/" title="Rerun Animation" icon="adjustments" >}}
{{< /cards >}}
7 changes: 5 additions & 2 deletions docs/content/docs/rerun_animation/_index.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,10 @@
linkTitle: Rerun Animation
title: Rerun Animation
prev: /docs/
next: /docs/
next:
---

About `...`
Flexible 3D animation data visualization.

## Overview
A `rerun-sdk` plugin & toolset to visualize 3D animation data. More details about `rerun-animation` can be found [here](https://moverseai.github.io/rerun-animation/).

0 comments on commit f3714ce

Please sign in to comment.