Skip to content

Commit

Permalink
Add more tutorials for training and usage of GenerativeRL.
Browse files Browse the repository at this point in the history
  • Loading branch information
zjowowen committed Jun 28, 2024
1 parent 6940902 commit 6c246a5
Show file tree
Hide file tree
Showing 4 changed files with 48 additions and 2 deletions.
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ English | [简体中文(Simplified Chinese)](https://github.com/opendilab/Genera
| [Linear VP SDE](https://arxiv.org/abs/2011.13456) |||
| [Generalized VP SDE](https://arxiv.org/abs/2209.15571) |||
| [Linear SDE](https://arxiv.org/abs/2206.00364) |||
| **Flow Model** | | |
| **Flow Model** [Colab](https://colab.research.google.com/drive/1vrxREVXKsSbnsv9G2CnKPVvrbFZleElI?usp=sharing) | | |
| [Independent Conditional Flow Matching](https://arxiv.org/abs/2302.00482) | 🚫 ||
| [Optimal Transport Conditional Flow Matching](https://arxiv.org/abs/2302.00482) | 🚫 ||

Expand Down
2 changes: 1 addition & 1 deletion README.zh.md
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@
| [Linear VP SDE](https://arxiv.org/abs/2011.13456) |||
| [Generalized VP SDE](https://arxiv.org/abs/2209.15571) |||
| [Linear SDE](https://arxiv.org/abs/2206.00364) |||
| **流模型** | | |
| **流模型** [Colab](https://colab.research.google.com/drive/1vrxREVXKsSbnsv9G2CnKPVvrbFZleElI?usp=sharing) | | |
| [Independent Conditional Flow Matching](https://arxiv.org/abs/2302.00482) | 🚫 ||
| [Optimal Transport Conditional Flow Matching](https://arxiv.org/abs/2302.00482) | 🚫 ||

Expand Down
23 changes: 23 additions & 0 deletions grl_pipelines/tutorials/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
# GenerativeRL Tutorials

English | [简体中文(Simplified Chinese)](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/README.zh.md)

## Train a Generative Model

### Diffusion Model

We provide a simple colab notebook to demonstrate how to build a diffusion model using the `grl` library. You can access the notebook [here](https://colab.research.google.com/drive/18yHUAmcMh_7xq2U6TBCtcLKX2y4YvNyk#scrollTo=aqtDAvG6cQ1V).

### Flow Model

We provide a simple colab notebook to demonstrate how to build a flow model using the `grl` library. You can access the notebook [here](https://colab.research.google.com/drive/1vrxREVXKsSbnsv9G2CnKPVvrbFZleElI?usp=drive_link).

## Evaluate a Generative Model

### Sample Generation

We provide a simple colab notebook to demonstrate how to generate samples from a trained generative model using the `grl` library. You can access the notebook [here](https://colab.research.google.com/drive/16jQhf1BDjtToxMZ4lDxB4IwGdRmr074j?usp=sharing).

### Density Estimation

We provide a simple colab notebook to demonstrate how to estimate the density of samples using a trained generative model using the `grl` library. You can access the notebook [here](https://colab.research.google.com/drive/1zHsW13n338YqX87AIWG26KLC4uKQL1ZP?usp=sharing).
23 changes: 23 additions & 0 deletions grl_pipelines/tutorials/README.zh.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
# GenerativeRL 教程

[英语 (English)](https://github.com/opendilab/GenerativeRL/tree/main/grl_pipelines/tutorials/README.md) | 简体中文

## 训练生成模型

### 扩散模型

我们提供了一个简单的 colab 笔记本,演示如何使用 `grl` 库构建扩散模型。您可以在[这里](https://colab.research.google.com/drive/18yHUAmcMh_7xq2U6TBCtcLKX2y4YvNyk#scrollTo=aqtDAvG6cQ1V)访问笔记本。

### 流模型

我们提供了一个简单的 colab 笔记本,演示如何使用 `grl` 库构建流模型。您可以在[这里](https://colab.research.google.com/drive/1vrxREVXKsSbnsv9G2CnKPVvrbFZleElI?usp=drive_link)访问笔记本。

## 评估生成模型

### 采样生成

我们提供了一个简单的 colab 笔记本,演示如何使用 `grl` 库从训练有素的生成模型生成样本。您可以在[这里](https://colab.research.google.com/drive/16jQhf1BDjtToxMZ4lDxB4IwGdRmr074j?usp=sharing)访问笔记本。

### 概率密度估计

我们提供了一个简单的 colab 笔记本,演示如何使用 `grl` 库从训练有素的生成模型估计样本的概率密度。您可以在[这里](https://colab.research.google.com/drive/1zHsW13n338YqX87AIWG26KLC4uKQL1ZP?usp=sharing)访问笔记本。

0 comments on commit 6c246a5

Please sign in to comment.