Search before asking I have searched the YOLOv8 issues and discussions and found no similar questions. Question from ultralytics import RTDETR import torch import numpy as np import onnxruntime def to_numpy(tensor): return tensor.detach(...
感谢您卓越的工作,请问如果想在不同batchsize下训练,取得一样的收敛速度,具体需要修改optimizer的哪些配置呢?我在8卡bs4或者4卡bs8的时候收敛速度相较于原配置慢很多。 Owner Peterandeclosed this ascompletedApr 19, 2024 Author Peterandereopened thisApr 23, 2024 ...