cxl-bupt

【队名】：cxl 【序号】：31 【论文】：PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud 【状态】：报名 【repo链接】：https://github.com/cxl-ustb/Point_RCNN

@lllyasviel Could you please add the ControlNet "weight" parameter (between 0 and 2, like A1111 extension) to this repo? I think this is one of the main parameters to tune...

the session is sim.session,after quantize. 我传入数据给量化后的模型的方式正确吗？非常期待您的回复 Is the method I used to pass in data to the quantified model correct? Looking forward to your reply very much

您好，非常感谢您的工作。有一个疑问就是，读取kspace的数据，进行逆傅里叶变换后数据范围太小了，要调整成一般图片的数值范围，一般是怎么做的呢？

> Because of different test datasets, the te Thank you.which dataset you used when you train the pretrain model MixDehazeNet-l?not RESIDE ITS?

> I train the model in RESIDE-ITS dataset and test it in SOTS-Indoor test dataset. You can see the details in my paper. Thank you very much for your reply.I...