minor edit

README.md

@@ -158,6 +158,15 @@ python ./tools/demo.py (Show all demo options)
 python ./tools/demo.py --demo 0 --frame 0 --numboxes 5 (Demo on frame 0 of COCO val set showing top 5 proposals)
 ```
 
+**Evaluate** the test result. This part is written in Matlab. First launch your Matlab in $FDBOX_ROOT. Then do the following:
+
+```Shell
+cd ./eval
+eval_fast_dbox
+plot_fast_dbox(name)
+```
+The evaluation output will be printed and the Recall-vs-NumOfProposals plots will be shown. 
+
 ### Extra-downloads
 
   Pre-computed Fast DeepBox proposals on COCO train, val, and test-dev. 

eval/eval_fast_dbox.m

@@ -1,17 +1,15 @@
 % Setup directories
 function eval_fast_dbox()
 name = 'fast-dbox-multiscale';
-%name = 'ebox_3_ss_73_iter_120000';
-suffix = ['fast_rcnn_dbox_' name];
-%load COCO annotations for specific categories
+suffix = ['results_' name];
 addpath('./MSCOCO/MatlabAPI');
 dataDir='./MSCOCO'; 
 split = 'val';
 year = '2014';
 dataType = [split year];
 annFile=sprintf('%s/annotations/instances_%s.json',dataDir,dataType);
 
-%% load coco non ovlap with imagenet categories
+%% load coco
 coco=CocoApi(annFile);
 imgIds = coco.getImgIds();
 num_imgs = numel(imgIds);

eval/plot_fast_rcnn.m → eval/plot_fast_dbox.m

@@ -1,5 +1,5 @@
-function plot_fast_rcnn(name)
-load(['fast_rcnn_dbox_' name '.mat']);
+function plot_fast_dbox(name)
+load(['result_' name '.mat']);
 dr_e = mean_edgebox./sum_gt;
 dr_ds = mean_dbox_Mprop./sum_gt; 
 thr_num = [1 2 5 10 20 50 100 200 500 1000 2000];