Closed zhaodongsun closed 6 years ago
When you are using only one GPU, the batch size is 1. When you are using N
GPUs, though BATCH_IMAGES=1
, your batch size is actually N
as each GPU processes one image in parallel, resulting in N
images processed together.
I've tried with 2 GPUs, and I got mAP@0.5=65.57, mAP@0.7=51.61, which is closer to the result from the paper.
Maybe smaller batch size will lead to the less accurate gradient? Do I need more epochs to get the same accuracy? @rogerwwww
Hi @zhaodongsun, Generally larger batch means faster convergence, while smaller batch will lead to higher accuracy with more epochs. You may have a try😃
I trained the model with VOC2012 for 22 epochs using only one GPU. I got lower accuracy and the results are as follows.