Update README.md

Author: kangben258

tools/eval/README.md

@@ -22,7 +22,8 @@ Supported datasets:
 - [ICDAR](#icdar2003)
 - [IIIT5K](#iiit5k)
 - [Mini Supervisely](#mini-supervisely)
-
+- [OTB](#otb)
+- 
 ## ImageNet
 
 ### Prepare data
@@ -211,4 +212,37 @@ Run evaluation on quantized model with the following command :
 
 ```shell
 python eval.py -m pphumanseg_q -d mini_supervisely -dr /path/to/pphumanseg
-```
+```
+
+
+## OTB
+The script is modified based on  [PyTracking](https://github.com/visionml/pytracking)
+
+### Prepare data
+
+Please download the mini_supervisely data from [here]() which includes the validation dataset and unzip it.. Organize files as follow:
+
+```shell
+$ tree -L 2 /path/to/otb
+.
+├── Basketball
+│   ├── groundtruth_rect.txt
+│   ├── img
+│   │   ├── xxxx.jpg
+├── Biker
+│   ├── groundtruth_rect.txt
+│   ├── img
+│   │   ├── xxxx.jpg
+            .
+            .
+            .
+├── OTB.json
+```
+
+### Evaluation
+
+Run evaluation with the following command:
+
+```shell
+python eval.py -m dasiamrpn -d OTB -dr /path/to/otb
+```