facebookresearch/maskrcnn-benchmark
Inference time increases linearly with batch size
Aberta
#294 aberto em 20 de dez. de 2018
help wanted
Métricas do repositório
- Stars
- (9.161 estrelas)
- Métricas de merge de PR
- (Métricas PR pendentes)
Description
❓ Questions and Help
I tested the batch inference,this is result batch size time 1 0.22 2 0.42 4 0.84 6 1.2 8 crash OOM Why big batchsize doesn't save time?