在下游任务做半监督学习，如何加载coco预训练模型？

[Stephen-Hao]

使用mmdetection默认的方式，在config文件里加入load_from的coco预训练路径会报模型参数不匹配的错误，怎么才能正确将coco预训练模型参数加载到student和teacher model里呢

[ligang-cs]

Sorry for late reply. You need to modify the code in Line 206 of train.py. Please use: runner.load_checkpoint(cfg.load_from, revise_keys=[(r'^', 'student.')])