From 8cbc1ed83f2dbe8f0b54a0594c5d3f46847b8770 Mon Sep 17 00:00:00 2001
From: liaoxingyu <sherlockliao01@gmail.com>
Date: Thu, 28 May 2020 20:01:20 +0800
Subject: [PATCH] update readme and instruction

---
 GETTING_STARTED.md |  3 ++-
 INSTALL.md         |  9 +++++++++
 README.md          | 25 ++++++++++++++++---------
 3 files changed, 27 insertions(+), 10 deletions(-)
 create mode 100644 INSTALL.md

diff --git a/GETTING_STARTED.md b/GETTING_STARTED.md
index 0821a85..b0236ab 100644
--- a/GETTING_STARTED.md
+++ b/GETTING_STARTED.md
@@ -2,7 +2,8 @@
 
 ## Prepare pretrained model
 
-If you use origin ResNet, you do not need to do anything. But if you want to use ResNet_ibn, you need to download pretrain model in [here](https://drive.google.com/open?id=1thS2B8UOSBi_cJX6zRy6YYRwz_nVFI_S). And then you can put it in `~/.cache/torch/checkpoints` or anywhere you like.
+If you use origin ResNet, you do not need to do anything. But if you want to use ResNet-ibn or ResNeSt, you need to download pretrain model in [here](https://drive.google.com/open?id=1thS2B8UOSBi_cJX6zRy6YYRwz_nVFI_S).
+And then you need to put it in `~/.cache/torch/checkpoints` or anywhere you like.
 
 Then you should set the pretrain model path in `configs/Base-bagtricks.yml`.
 
diff --git a/INSTALL.md b/INSTALL.md
new file mode 100644
index 0000000..5f582ac
--- /dev/null
+++ b/INSTALL.md
@@ -0,0 +1,9 @@
+# Installation
+
+## Requirements
+
+- Linux or macOS with python ≥ 3.6
+- PyTorch ≥ 1.0
+- torchvision that matches the Pytorch installation. You can install them together at [pytorch.org]() to make sure of this.
+- [yacs](https://github.com/rbgirshick/yacs)
+- Cython (optional to compile evaluation)
diff --git a/README.md b/README.md
index a9e52a0..87ea8fa 100644
--- a/README.md
+++ b/README.md
@@ -1,20 +1,27 @@
 # FastReID
 
-FastReID is a research platform that implements state-of-the-art re-identification algorithms.
+FastReID is a research platform that implements state-of-the-art re-identification algorithms. It is a groud-up rewrite of the previous verson, [reid strong baseline](https://github.com/michuanhaohao/reid-strong-baseline).
+
+## What's New
+
+- Remove [ignite](https://github.com/pytorch/ignite)(a high-level library) dependency and powered by [PyTorch](https://pytorch.org/).
+- Includes more features such as circle loss, visualizing ranklist and label, SoTA results on intra-domain, cross-domain and partial reid, testing on multi-datasets at the same time, etc.
+- Can be used as a library to support [different projects](https://github.com/JDAI-CV/fast-reid/tree/master/projects) on top of it. We'll open source more research projects in this way.
+- It trains much faster.
+
+See our [zhihu blog]() to learn more about fastreid.
+
+## Installation
+
+See [INSTALL.md](https://github.com/JDAI-CV/fast-reid/blob/master/INSTALL.md).
 
 ## Quick Start
 
 The designed architecture follows this guide [PyTorch-Project-Template](https://github.com/L1aoXingyu/PyTorch-Project-Template), you can check each folder's purpose by yourself.
 
-See GETTING_STARTED.md.
+See [GETTING_STARTED.md](https://github.com/JDAI-CV/fast-reid/blob/master/GETTING_STARTED.md).
 
-Learn more at out documentation. And see projects/ for some projects that are build on top of fastreid.
-
-Install dependencies:
-
-- [pytorch 1.0.0+](https://pytorch.org/)
-- torchvision
-- [yacs](https://github.com/rbgirshick/yacs)
+Learn more at out [documentation](). And see [projects/](https://github.com/JDAI-CV/fast-reid/tree/master/projects) for some projects that are build on top of fastreid.
 
 ## Model Zoo and Baselines