Giters

sejong-rcv / MLPD-Multi-Label-Pedestrian-Detection

[RA-L with IROS2021] Multi-Label Pedestrian Detection in Multispectral data

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Train on custom data

TRTmm opened this issue · comments

commented

Hi , since i am very interested in your work, i like to reproduce it with my own dataset but i got this error .

Error : stack expects each tensor to be equal size, but got [3, 720, 1280] at entry 0 and [3, 512, 640] at entry 1
(NB : my image dimension is 1280x720)

commented

Hi, thank you for your interest in our work. We recommend simply resizing the input shape to 512*640 as it is used in our paper. However, if you indeed need to use the original resolution, then you will need to change some of the codes for the initial parameters of prior anchor boxes. Please, refer to the link and change some parameters after referring to SSD tutorial. Thank you.