Ziyue Feng
Ziyue Feng
we can't make a two-level folder with one "mkdir" command, have to first make the "models" and then "bts_eigen_v2_att_rank_3"
@chrischoy Could this code use multi gpu? I added this to the main.py: `if torch.cuda.device_count() > 1:` ` print("Let's use", torch.cuda.device_count(), "GPUs!")` ` model = torch.nn.DataParallel(model)` ` model = model.to(torch.device("cuda:0"))`...
I downloaded the GT from manydepth’s repo On Tue, May 10, 2022 at 5:11 AM JumpingJessie ***@***.***> wrote: > @fengziyue > > Hi, have you solved the problem? Could you...
Hi @Renatusphere : The depth in the `trainer.py` is normalized and does not reflect the absolute scale. However, the pose net and the depth net are sharing the same scale...
Hi @GANWANSHUI : Thank you for your interest. In the KITTI dataset, the valid depth range is 0-80m, so we roughly scale the predicted depth to the real-world metric and...
`evaluate_depth.py` 的结果是四舍五入到小数点后3位的。另外它和训练时的val函数的实现有一点细微的差别，这个量级的误差可以忽略的。
@Owen-Liuyuxuan Hi, have you tried the latest Pytorch/CUDA version?
> > > Actually I've done the same experiments and if you train for 30 epochs you can get a better result which is nearly the same as paper. >...
> Hi - really sorry for the delay in getting back on this, I was looking at it, but then had CVPR submission and some vacation to take. I will...