wordpress的x站模板,wordpress可视化编辑器 windows,国内最近重大新闻2024,手工做皮具国外的网站文章目录 方法一方法二 当yolo在训练的时候#xff0c;如果训练中断或者出现异常#xff0c;可通过修改代码#xff0c;从上一次断掉处重新训练#xff0c;实现断点续训。
方法一
第一种方法#xff1a; 按照官方给出的恢复训练代码#xff0c;用yolo命令格式#xff… 文章目录 方法一方法二 当yolo在训练的时候如果训练中断或者出现异常可通过修改代码从上一次断掉处重新训练实现断点续训。
方法一
第一种方法 按照官方给出的恢复训练代码用yolo命令格式这种情况必须是环境以安装了yolo和ultralytics两个包
运行命令
yolo taskdetect modetrain modelruns/detect/exp/weights/last.pt dataultralytics/datasets/test.yaml epochs100 saveTrue resumeTrue方法二 在ultralytics/yolo/engine/trainer.py中找到check_resume和resume_training。 注释check_resume中resume self.args.resume改成需要断点恢复的last.pt。 在resume_training里面添加一行ckpt的值
def check_resume(self):# resume self.args.resume # 注释掉这一行resume runs/detect/exp/weights/last.pt; # 从最后的last.pt开始继续训练if resume:try:last Path(check_file(resume) if isinstance(resume, (str,Path)) and Path(resume).exists() else get_latest_run())self.args get_cfg(attempt_load_weights(last).args)self.args.model, resume str(last), True # reinstateexcept Exception as e:raise FileNotFoundError(Resume checkpoint not found. Please pass a valid checkpoint to resume from, i.e. yolo train resume modelpath/to/last.pt) from eself.resume resumedef resume_training(self, ckpt):ckpt torch.load(runs/detect/exp/weights/last.pt) # 加载预训练模型if ckpt is None:returnbest_fitness 0.0start_epoch ckpt[epoch] 1if ckpt[optimizer] is not None:self.optimizer.load_state_dict(ckpt[optimizer]) # optimizerbest_fitness ckpt[best_fitness]if self.ema and ckpt.get(ema):self.ema.ema.load_state_dict(ckpt[ema].float().state_dict()) # EMAself.ema.updates ckpt[updates]if self.resume:assert start_epoch 0, \f{self.args.model} training to {self.epochs} epochs is finished, nothing to resume.\n \fStart a new training without --resume, i.e. yolo task... modetrain model{self.args.model}LOGGER.info(fResuming training from {self.args.model} from epoch {start_epoch 1} to {self.epochs} total epochs)if self.epochs start_epoch:LOGGER.info(f{self.model} has been trained for {ckpt[epoch]} epochs. Fine-tuning for {self.epochs} more epochs.)self.epochs ckpt[epoch] # finetune additional epochsself.best_fitness best_fitnessself.start_epoch start_epoch最后记住断点续训结束后将trainer.py还原否则影响下次训练
