Darcy

About ResNet18？

3

Have you tried this structure on ResNet18? Does it work for light-weight network?

Question about the whole algorithm?

3

Is your proposed algorithm trained in the supervised way? I see that the input of STTR contains GT disparity and occlusion region during training phase.

Unable to achieve convergence on both GPU and CPU

4

### Question Description I am attempting to fit an exact GP regression on a dataset of ~ 10000 points. The `train_x` is `3×7740×2` (repeated from the base shape `7740×2`) and...

The code couldn't run as wish. I have run `sudo apt-get install ninja-build` on ubuntu18.04, but the error is as below: ``` Traceback (most recent call last): File "/home/dell/Codes/mono2++/train.py", line...

I don't understand why the offset needs to be set to -4. ``` ate_rmse, rpe_trans, rpe_rot, trans_error, rpe_trans_e, rpe_rot_e = eval(os.path.join(args.input, 'groundtruth.txt'), os.path.join(args.outpath, 'trajectory.freiburg'), offset=-4) ```