Add script to download COCO val2017

Signed-off-by: xavier <micaelaverucchi@gmail.com>

README.md

@@ -118,7 +118,12 @@ this will genereate resnet101_cnet.rt and dla34_cnet.rt file that can be used fo
 ## mAP demo
 To compute mAP, precision, recall and f1score, run the map_demo.
 
-The following parameters are needed:
+A validation set is needed. To download COCO_val2017 run (form the root folder): 
+```
+bash download_validation.sh 
+```
+
+To compute the map, the following parameters are needed:
 ```
 ./map_demo <network rt> <network type [y|c]> <labels file path> <config file path>
 ```
@@ -131,5 +136,6 @@ where
 Example:
 
 ```
-./map_demo dla34_cnet.rt c path/to/labelsCOCO_val2017.txt ../demo/config.yaml
+cd build
+./map_demo dla34_cnet.rt c ../demo/COCO_val2017/all_labels.txt ../demo/config.yaml
 ```

demo/demo/map.cpp

@@ -31,7 +31,7 @@ int main(int argc, char *argv[])
     char ntype = 'y';
     char *config_filename = "../demo/config.yaml";
     char * net = "yolo3.rt";
-    char * labels_path = "/media/887E650E7E64F67A/val2017/all_labels2017.txt";
+    char * labels_path = "../demo/COCO_val2017/all_labels.txt";
     bool show = false;
     bool write_dets = false;
     int n_images = 1000;
@@ -42,7 +42,7 @@ int main(int argc, char *argv[])
         ntype = argv[2][0];    
     if(argc > 3)
         labels_path = argv[3]; 
-    if(argc > 3)
+    if(argc > 4)
         config_filename = argv[4]; 
 
     tk::dnn::Yolo3Detection yolo;

download_validation.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+cd demo
+wget https://cloud.hipert.unimore.it/s/LNxBDk4wzqXPL8c/download -O COCO_val2017.zip
+unzip -d COCO_val2017 COCO_val2017.zip
+rm COCO_val2017.zip
+cd COCO_val2017/
+realpath labels/* > all_labels.txt