乖奕虎
change https://github.com/weiaicunzai/pytorch-cifar100/blob/1fe2ec40dc05cd81fee6ab23de09b99fdb0d282f/train.py#L148 to input_tensor = torch.Tensor(1, 3, 32, 32).cuda()
Fixed pose+= [(ll+rl)/2.0, (lu+ru)/2.0] steady_pose = [] if error > 100: # large error means tracking fails: reinitialize pose estimator # at the same time, keep sending the same information...
> > I turn off the bluetooth ,the error does not happen again.Maybe you can try.If you find any other solution please tell me. > > This is my solution:...
Will any one review this commit?
> I am ok if we add an assert so that we still have a chance to catch the root cause but avoiding crash in production. @GuaiYiHu Can you add...
> From PR review triage: @GuaiYiHu are you interested in continuing with this PR? If so, it looks like the next step is to follow-up on the feedback from @chunhtai....
> From PR review triage: @GuaiYiHu are you interested in continuing with this PR? If so, it looks like the next step is to follow-up on the feedback from @chunhtai....
@chunhtai Pushed again, all checks have passed, please review, thanks a lot.