From d53415bc105fa73e33f95b587699af07c761d77b Mon Sep 17 00:00:00 2001
From: Frank Lee <somerlee.9@gmail.com>
Date: Sat, 12 Nov 2022 16:38:41 +0800
Subject: [PATCH] [tutorial] added data script and updated readme (#1916)

---
 examples/tutorial/.gitignore          |  1 +
 examples/tutorial/README.md           | 34 ++++++++++++++++++++++-----
 examples/tutorial/download_cifar10.py | 13 ++++++++++
 3 files changed, 42 insertions(+), 6 deletions(-)
 create mode 100644 examples/tutorial/.gitignore
 create mode 100644 examples/tutorial/download_cifar10.py

diff --git a/examples/tutorial/.gitignore b/examples/tutorial/.gitignore
new file mode 100644
index 000000000..8fce60300
--- /dev/null
+++ b/examples/tutorial/.gitignore
@@ -0,0 +1 @@
+data/
diff --git a/examples/tutorial/README.md b/examples/tutorial/README.md
index 04436e0dd..8a5831343 100644
--- a/examples/tutorial/README.md
+++ b/examples/tutorial/README.md
@@ -7,18 +7,33 @@ Welcome to the [Colossal-AI](https://github.com/hpcaitech/ColossalAI) tutorial,
 
 [Colossal-AI](https://github.com/hpcaitech/ColossalAI), a unified deep learning system for the big model era, integrates
 many advanced technologies such as multi-dimensional tensor parallelism, sequence parallelism, heterogeneous memory management,
-large-scale optimization, adaptive task scheduling, etc. By using Colossal-AI, we could help users to efficiently and 
+large-scale optimization, adaptive task scheduling, etc. By using Colossal-AI, we could help users to efficiently and
 quickly deploy large AI model training and inference, reducing large AI model training budgets and scaling down the labor cost of learning and deployment.
 
 ### 🚀 Quick Links
 
 [**Colossal-AI**](https://github.com/hpcaitech/ColossalAI) |
-[**Paper**](https://arxiv.org/abs/2110.14883) | 
-[**Documentation**](https://www.colossalai.org/) | 
-[**Forum**](https://github.com/hpcaitech/ColossalAI/discussions) | 
+[**Paper**](https://arxiv.org/abs/2110.14883) |
+[**Documentation**](https://www.colossalai.org/) |
+[**Forum**](https://github.com/hpcaitech/ColossalAI/discussions) |
 [**Slack**](https://join.slack.com/t/colossalaiworkspace/shared_invite/zt-z7b26eeb-CBp7jouvu~r0~lcFzX832w)
 
 
+## Prerequisite
+
+To run this example, you only need to have PyTorch and Colossal-AI installed. A sample script to download the dependencies is given below.
+
+```
+# install torch 1.12 with CUDA 11.3
+# visit https://pytorch.org/get-started/locally/ to download other versions
+pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113
+
+# install latest ColossalAI
+# visit https://colossalai.org/download to download corresponding version of Colossal-AI
+pip install colossalai==0.1.11+torch1.12cu11.3 -f https://release.colossalai.org
+```
+
+
 ## Table of Content
 
  - Multi-dimensional Parallelism
@@ -43,7 +58,15 @@ quickly deploy large AI model training and inference, reducing large AI model tr
  - Acceleration of Stable Diffusion
    - Stable Diffusion with Lightning
    - Try Lightning Colossal-AI strategy to optimize memory and accelerate speed
-      
+
+## Prepare Common Dataset
+
+**This tutorial folder aims to let the user to quickly try out the training scripts**. One major task for deep learning is data preparataion. To save time on data preparation, we use `CIFAR10` for most tutorials and synthetic datasets if the dataset required is too large. To make the `CIFAR10` dataset shared across the different examples, it should be downloaded in tutorial root directory with the following command.
+
+```python
+python download_cifar10.py
+```
+
 
 ## Discussion
 
@@ -51,4 +74,3 @@ Discussion about the [Colossal-AI](https://github.com/hpcaitech/ColossalAI) proj
 If you think there is a need to discuss anything, you may jump to our [Slack](https://join.slack.com/t/colossalaiworkspace/shared_invite/zt-z7b26eeb-CBp7jouvu~r0~lcFzX832w).
 
 If you encounter any problem while running these tutorials, you may want to raise an [issue](https://github.com/hpcaitech/ColossalAI/issues/new/choose) in this repository.
-
diff --git a/examples/tutorial/download_cifar10.py b/examples/tutorial/download_cifar10.py
new file mode 100644
index 000000000..5c6b6988a
--- /dev/null
+++ b/examples/tutorial/download_cifar10.py
@@ -0,0 +1,13 @@
+import os
+
+from torchvision.datasets import CIFAR10
+
+
+def main():
+    dir_path = os.path.dirname(os.path.realpath(__file__))
+    data_root = os.path.join(dir_path, 'data')
+    dataset = CIFAR10(root=data_root, download=True)
+
+
+if __name__ == '__main__':
+    main()