pytorcher
pytorcher
@StephanPan 怎么样，搞清楚了吗？
请问如何得到的呢
thanks a lot!
@zhanghongruiupup have you find why?
@krrish94 me too, what this line for ? ray_directions = torch.sum( directions[..., None, :] * tform_cam2world[:3, :3], dim=-1 )`
@wangshusen 王老师，看了您的RL课程收益匪浅，我看课程主要偏向理论和公式，想上手下RL，有没有推荐的github上的代码去研读？
谢谢您的回复哈。请问refinement代码用于one stage的实现是怎么个过程呢？代码是否已经做了实现？如果是，我去看下代码。因为我看之前的issue，貌似现在代码还不完善还在开发中，对吧？
hi,@isamu-isozaki ，@patil-suraj @williamberman: https://github.com/huggingface/open-muse/blob/0ba7d0100c865d77d1ef63f3502acb1bd8729ff3/training/train_muse.py#L162 here, as the torch doc says, it returns the indices that sort a tensor along a given dimension in ascending order by value https://pytorch.org/docs/stable/generated/torch.argsort.html#torch.argsort. I think...