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
hasibzunair opened this issue 2 years ago · 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.
SEQS_PER_BATCH=8
configs/softmax_triplet.yml