From f67b3845ebfb072964fb23c7e47159d73055ae02 Mon Sep 17 00:00:00 2001
From: Sawrav Chowdhury <43489196+sawravchy@users.noreply.github.com>
Date: Sat, 25 Jul 2020 02:43:04 +0600
Subject: [PATCH 1/3] Update README.md

---
 README.md | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 061e0d4..85c140d 100644
--- a/README.md
+++ b/README.md
@@ -4,10 +4,9 @@ STAC is a simple yet effective SSL framework for visual object detection along
 with a data augmentation strategy. STAC deploys highly confident pseudo labels of
 localized objects from an unlabeled image and updates the model by enforcing
 consistency via strong augmentation.
-
+<p align=center>
 <img src="docs/diagram.png" width="800">
-
-__This code is only used for research. This is not an official Google product.__
+</p>
 
 
 # Instruction
@@ -205,6 +204,9 @@ tensorboard --logdir=${PRJROOT}/detection/train_log
   booktitle={arXiv:2005.04757}
 }
 ```
+## Disclaimer
+
+This code is only used for research. This is not an official Google product.
 
 # Acknowledgement
 

From e3000e8ec7bd7ef44fa2f15d048e48dffffc9ea4 Mon Sep 17 00:00:00 2001
From: Sawrav Chowdhury <43489196+sawravchy@users.noreply.github.com>
Date: Sat, 25 Jul 2020 02:58:30 +0600
Subject: [PATCH 2/3] Update README.md

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 85c140d..d42311f 100644
--- a/README.md
+++ b/README.md
@@ -4,9 +4,9 @@ STAC is a simple yet effective SSL framework for visual object detection along
 with a data augmentation strategy. STAC deploys highly confident pseudo labels of
 localized objects from an unlabeled image and updates the model by enforcing
 consistency via strong augmentation.
-<p align=center>
+
 <img src="docs/diagram.png" width="800">
-</p>
+
 
 
 # Instruction

From aa55294f41ba836199943016e4c2a5084bd8a1f3 Mon Sep 17 00:00:00 2001
From: Sawrav Chowdhury <43489196+sawravchy@users.noreply.github.com>
Date: Sat, 25 Jul 2020 03:11:11 +0600
Subject: [PATCH 3/3] Update README.md

---
 README.md | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index d42311f..67b8525 100644
--- a/README.md
+++ b/README.md
@@ -64,17 +64,17 @@ wget http://models.tensorpack.com/FasterRCNN/ImageNet-R50-AlignPadding.npz
 
 There are three steps:
 - __1.__ Train a standard detector on labeled data
-(`detection/scripts/coco/train_stg1.sh`).
+[`detection/scripts/coco/train_stg1.sh`](./detection/scripts/coco/train_stg1.sh).
 - __2.__ Predict pseudo boxes and labels of unlabeled
-data using the trained detector (`detection/scripts/coco/eval_stg1.sh`).
+data using the trained detector [`detection/scripts/coco/eval_stg1.sh`](./detection/scripts/coco/eval_stg1.sh).
 - __3.__ Use labeled data and unlabeled data with
 pseudo labels to train a STAC detector
-(`detection/scripts/coco/train_stg2.sh`).
+[`detection/scripts/coco/train_stg2.sh`](./detection/scripts/coco/train_stg2.sh).
 
-Besides instruction at here, __`detection/scripts/coco/train_stac.sh`__
+Besides instruction at here, [__`detection/scripts/coco/train_stac.sh`__](./detection/scripts/coco/train_stac.sh)
 provides a combined script to train STAC.
 
-__`detection/scripts/voc/train_stac.sh`__ is a combined script to train STAC on PASCAL VOC.
+[__`detection/scripts/voc/train_stac.sh`__](./detection/scripts/voc/train_stac.sh) is a combined script to train STAC on PASCAL VOC.
 
 The following example use labeled data as 10% train2017 and rest 90% train2017 data
 as unlabeled data.