Wang Shizun
Wang Shizun
我这里运行运行原代码没有问题呢，你有改动代码吗，或者参数输入正确吗
Hi @nikitakaraevv, I followed your instructions and it is generating annotations now, but the generation speed is quite slow on my end, roughly 2 seconds per iteration. Is it the...
Thanks for your prompt reply. May I know which dataset is swapped?
@puyiwen In Dust3r, it's scale-invariant depth. If you want metric depth, you can check out Mast3r.
@puyiwen Sorry I didn't run the liner head model. But since the training data is normalized in dust3r, all output depth of different dust3r variant should be scale-invariant.
@CrispyFeSo4 Hi, I also encountered this problem. It was due to an incomplete compilation of RoPE. Recompiling should fix it.