The main difference between general classification task and few shot classification task is the data usage. Therefore, the design of MMFewShot targets at data flows for few shot setting based on mmdet. Additionally, the modules in mmdet can be imported and reused in the code or config.
Since MMFewShot is built upon the mmdet, all the datasets in mmdet can be configured in the config file. If user want to use the dataset from mmdet, please refer to mmdet for more details.
In MMFewShot, there are three important components for fetching data:
ann_cfg
and filtering images and annotations for few shot setting.In summary, we currently support 4 different data flow for training:
For testing:
QuerySupportEvalHook
. More implementation details can refer to mmfewshot.detection.core.evaluation.eval_hooks
More usage details and customization can refer to Tutorial 2: Adding New Dataset
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。