self.register_momentum_hook(momentum_config) self.register_optimizer_hook(optimizer_config) self.register_checkpoint_hook(checkpoint_config) self.register_hook(IterTimerHook()) self.register_logger_hooks(log_config) call_hook call_hook很简单,就是遍历self._hooks,依次调用指定的方法,再介绍之前,先快速过...
log │ └── vis_data │ ├── 20230506_101711.json │ ├── config.py │ └── scalars.json ├── centerpoint_pillar02_second_secfpn_8xb4-cyclic-20e_livox.py ├── epoch_20.pth └── last_checkpoint epoch_20.pth结构为: . └── archive ├── data │ ├── 0 │ ...
(2)绘制分类损失、回归损失曲线图,保存图片为对应的 pdf 文件 注:--keys 这里的参数可以替换成log.json中的数据参数。(3)在相同图像中比较两次运行结果的 bbox mAP 注:注意json文件中bbox_mAP的名字,有可能是0_bbox_mAP等... (4)计算平均训练速度 注:这里--include-outliers的作用是指定在计算训练迭代的...
Search or jump to... Search code, repositories, users, issues, pull requests... Provide feedback We read every piece of feedback, and take your input very seriously. Include my email address so I can be contacted Cancel Submit feedback Saved searches Use saved searches to filter your...
By use case DevSecOps DevOps CI/CD View all use cases By industry Healthcare Financial services Manufacturing Government View all industries View all solutions Resources Topics AI DevOps Security Software Development View all Explore Learning Pathways White papers, Ebooks, Webinars ...
logging.basicConfig(filename='example.log',level=logging.INFO) logging.debug('This message should go to the log file') logging.info('So should this') logging.warning('And this, too') 其中下面这句中的level=loggin.INFO意思是,把日志纪录级别设置为INFO,也就是说,只有比日志是INFO或比INFO级别更...
print_log( f'\nEvaluating {dataset.ann_file} with ' f'{len(results_per_dataset)} images now', logger=logger) eval_results_per_dataset = dataset.evaluate( results_per_dataset, logger=logger, **kwargs) dataset_idx += 1 for k, v in eval_results_per_dataset.items(): total...
配置优化器中是否使用梯度剪裁grad_clipoptimizer_config=dict(grad_clip=None)# configuration of saving checkpoints periodically# 配置间隔interval个epoch保存一次训练参数checkpoint_config=dict(interval=1)# save log periodically and multiple hooks can be used simultaneouslylog_config=dict(interval=100,hooks=[...
(cfg.data.train)ifcfg.checkpoint_configisnotNone:# save mmdet version, config file content and class names in checkpoints as meta data# 要注意的是,以前发布的模型是不存这个类别等信息的,# 用的默认COCO或者VOC参数,所以如果用以前训练好的模型检测时会提醒warning一下,无伤大雅cfg.checkpoint_config....
config: model config 文件的路径。 prediction_path: 使用 tools/test.py 输出的 pickle 格式结果文件。 show_dir: 绘制真实标注框与预测框的图像存放目录。 --show:决定是否展示绘制 box 后的图片,默认值为 False。 --wait-time: show 时间的间隔,若为 0 表示持续显示。