Unverified 提交 9f98201d authored 作者: Glenn Jocher's avatar Glenn Jocher 提交者: GitHub

W&B DDP fix 2 (#2587)

Revert unintentional change to test batch sizes caused by PR https://github.com/ultralytics/yolov5/pull/2125
上级 2bcc89d7
...@@ -349,7 +349,7 @@ def train(hyp, opt, device, tb_writer=None): ...@@ -349,7 +349,7 @@ def train(hyp, opt, device, tb_writer=None):
if not opt.notest or final_epoch: # Calculate mAP if not opt.notest or final_epoch: # Calculate mAP
wandb_logger.current_epoch = epoch + 1 wandb_logger.current_epoch = epoch + 1
results, maps, times = test.test(data_dict, results, maps, times = test.test(data_dict,
batch_size=total_batch_size, batch_size=batch_size * 2,
imgsz=imgsz_test, imgsz=imgsz_test,
model=ema.ema, model=ema.ema,
single_cls=opt.single_cls, single_cls=opt.single_cls,
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论