Update README.md

Author: amiralush

README.md

@@ -5,42 +5,10 @@ FastDup is a tool for fast detection of duplicate and near duplicate images. Fas
 
 ![alt text](https://github.com/visualdatabase/fastdup/blob/main/gallery/git_main-min.png)
 
-## Quick Installation
-For Python 3.7 and 3.8
-```python
-pip install fastdup
-```
-
-[Install from stable release](INSTALL.md)
-
-
-## Running the code
-
-### Python
-```python
-python3
-import fastdup
-fastdup.run(input_dir="/path/to/your/folder", work_dir="/path/to/your/folder") #main running function
-```
-  
-### C++
-```bash
-/usr/bin/fastdup /path/to/your/folder --work_dir="/tmp/fastdup_files"
-```
-
-[Detailed running instructions](RUN.md)
-
-
-
-### Support for s3 cloud/ google storage
-[Detailed instructions](CLOUD.md)
-
-
 ## Results on Key Datasets
-We have thourougly tested fastdup across various famous computer-vision dataset. Ranging from Academic datasets to Kaggle competitions. A key finding we have made using FastDup is that there are ~1.2M (!) duplicate images on the ImageNet21K dataset, a new unknown result! Full results are below.
+We have thourougly tested fastdup across various famous visual dataset. Ranging from Academic datasets to Kaggle competitions. A key finding we have made using FastDup is that there are ~1.2M (!) duplicate images on the ImageNet21K dataset, a new unknown result! Full results are below.
 
 ### FastDup is FAST
-
 |Dataset	        |Total Images	|Owner			|Image Res     |cost [$]|spot cost [$]|processing [sec]|throughput [1/sec]|
 |-----------------------|---------------|-----------------------|--------------|--------|-------|-------|-----|
 |[imagenet21k-resized](https://www.image-net.org/challenges/LSVRC/)	|11,582,724	|alibaba/academy	|133x200	|4.98	|1.24	|11,561	|1,002|
@@ -58,8 +26,6 @@ We have thourougly tested fastdup across various famous computer-vision dataset.
 * We run on the full ImageNet dataset (11.5M images) to compare all pairs of images in less than 3 hours WITHOUT a GPU (with Google cloud cost of 5$).
 
 ### FastDup is ACCURATE
-
-
 Dataset|	Identical Pairs|	Near-Identical Pairs
 -------|----------------------|--------------------
 [imagenet21k-resized](https://www.image-net.org/challenges/LSVRC/)	|1,194,059|	53,358
@@ -76,3 +42,33 @@ Dataset|	Identical Pairs|	Near-Identical Pairs
 [snakeclef2022-fgvc9](https://www.kaggle.com/competitions/snakeclef2022/data)	|6,953	|33,128
 [fungiclef2022-fgvc9](https://www.kaggle.com/competitions/fungiclef2022/data)	|2,205	|75
 [hotel-id-to-combat-human-trafficking-2022-fgvc9](https://www.kaggle.com/competitions/hotel-id-to-combat-human-trafficking-2022-fgvc9/data)|	3,544	|2,704
+
+## Quick Installation
+For Python 3.7 and 3.8
+```python
+pip install fastdup
+```
+
+[Install from stable release](INSTALL.md)
+
+
+## Running the code
+
+### Python
+```python
+python3
+import fastdup
+fastdup.run(input_dir="/path/to/your/folder", work_dir="/path/to/your/folder") #main running function
+```
+  
+### C++
+```bash
+/usr/bin/fastdup /path/to/your/folder --work_dir="/tmp/fastdup_files"
+```
+
+[Detailed running instructions](RUN.md)
+
+
+
+### Support for s3 cloud/ google storage
+[Detailed instructions](CLOUD.md)