In caffe, py-faster-rcnn, "scores" return a large matrix, why? - neural-network

Question

I use the py-faster-rcnn demo to build further of my project with 20 classes.
However, I am trying to gain the softmax, last layer probability of my classes.
For example:
# Load the demo image
im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)
im = cv2.imread(im_file)
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = im_detect(net, im)
timer.toc()
print ('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = 0.8
NMS_THRESH = 0.3
for cls_ind, cls in enumerate(CLASSES[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 4*cls_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, :]
vis_detections(im, cls, dets, thresh=CONF_THRESH)
print scores
While I do the print scores, it gives me a very large matrix output,
instead of 1 x 20 . I am not sure why, and how can I get the last probability matrix?
Thanks

Answer 1

The raw scores the detector outputs include overlapping detections and very low score detections as well.
Note that only after applying non-maximal suppression (aka "nms") with NMS_THRESH=0.3 the function vis_detection only displays detections with confidence larger than CONF_THRESH=0.8.
So, if you want to look at the "true" objects, you need to check inside vis_detection and check only the detections it renders on the image.