WangYQ9 / VideoReID_PSTA

Code for ICCV 2021 paper Pyramid Spatial-Temporal Aggregation for Video-based Person Re-Identification

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

train on single GPU

hasibzunair opened this issue · comments

Hi, wanted to know if it's possible to run training on a single 12GB memory GPU. I'm getting the following error after reducing batch size, both SEQS_PER_BATCH=8 and test SEQS_PER_BATCH=8 in the configs/softmax_triplet.yml file.

image