AI攻城狮

use pseco

# RCNN stage """ obtain proposals """ if self.use_teacher_proposal: proposal_list = tea_proposals else : proposal_cfg = self.student.train_cfg.get( "rpn_proposal", self.student.test_cfg.rpn ) proposal_list = self.student.rpn_head.get_bboxes( *stu_rpn_outs, img_metas_student, cfg=proposal_cfg ) 我看代码中self.use_teacher_proposal=True,但tea_proposals来源于weak img-->teach model。论文中说“We...

> Proposals是由teacher model的RPN产生的。在student的训练过程中，虽然student RPN会产生自己的proposals，但是没有被使用。而是把teacher的proposals直接拿来训练student了。 很感谢您的解答，我还有一个问题，论文中指出这个方法也适用于单阶段，如果是单阶段的话，那么质量得分q的生成是student_model+teacher_head生成候选框吗？

出现这个错误:Timed out waiting for process to appear on device

how to fix it? Traceback (most recent call last): File "/home/yyds/anaconda3/envs/rvc/lib/python3.9/site-packages/gradio/routes.py", line 414, in run_predict output = await app.get_blocks().process_api( File "/home/yyds/anaconda3/envs/rvc/lib/python3.9/site-packages/gradio/blocks.py", line 1323, in process_api data = self.postprocess_data(fn_index, result["prediction"], state)...

这个是yolov8的onnx模型，应该没什么特殊结构吧