search

VDIGPKU / CFENet

Comprehensive Feature Enhancement Module for Single-Shot Object Detector
198 stars 36 forks source link

Help #15

Open door5719 opened 5 years ago

door5719 commented 5 years ago

Whitout your demo code, I try draw detect result on pic. In test.py, line 64: ........ out = net(x) boxes, scores = detector.forward(out,priors) detect_time = _t['im_detect'].toc() boxes = boxes[0] scores=scores[0] boxes *= scale boxes = boxes.cpu().numpy() scores = scores.cpu().numpy() ...... after these codes, I think with boxes /scores I can draw box of object detect result on input pic(x was get from this pic) ,whit nms , I will get the right results. Is it right?

door5719 commented 5 years ago

boxes.shape = (11620, 4) scores.shape=（11620,81)