Evaluation of accuracy

[Usernamezhx]

hi playerkk
I'm sorry to bother you again. after about two day training. i get the vgg16_faster_rcnn_iter_80000.caffemodel. and then I run
python ./tools/run_face_detection_on_fddb.py --gpu=0
after that the screen display the number such:1 3.448 6.897 10.345 ..... and then I check the code: run_face_detection_on_fddb.py
I find this : sys.stdout.write('%.3f ' % ((idx + 1) / len(image_names) * 100)).
In addition to that. I want to know how do you evaluat the accuracy. after that : scores, boxes = im_detect(net, im) . we will get the scores, boxes .
But I was confused for the next code:
` cls_ind = 1
cls_boxes = boxes[:, 4cls_ind:4(cls_ind + 1)]
cls_scores = scores[:, cls_ind]
dets = np.hstack((cls_boxes,
cls_scores[:, np.newaxis])).astype(np.float32)
keep = nms(dets, NMS_THRESH)
dets = dets[keep, :]

  keep = np.where(dets[:, 4] > CONF_THRESH)
  dets = dets[keep]

  # vis_detections(im, 'face', dets, CONF_THRESH)

  dets[:, 2] = dets[:, 2] - dets[:, 0] + 1
  dets[:, 3] = dets[:, 3] - dets[:, 1] + 1`

Thanks in advance. hope your reply.

[ghost]

hi @Usernamezhx,I'm a new guy,sorry to bother you .i was in the training model when there was a problem:
Path does not exist:data/WIDER/wider_face_train_annot.txt.
i would like to know WIDER directory in addition to WIDER_test,WIDER_train,WIDER_val,what else should i need.
Hope to get your help .thanks a lot!

[Usernamezhx]

@HaoXiedo
you should pay attention to the Prepare training data and the step 3 . Download the file and put it under the WIDER directory

[ghost]

@Usernamezhx thank you very much.I dowmload the file through your csdn blog,it started working!

[playerkk]

@Usernamezhx

1. sys.stdout.write('%.3f ' % ((idx + 1) / len(image_names) * 100)) prints out the progress
2. Since there are only two classes for face detection (background and face), we can simply get the score of being a face for a bounding box with cls_ind=1 (0 is for the score of being background).
3. You might find the evaluation script of FDDB helpful http://vis-www.cs.umass.edu/fddb/evaluation.tgz