isJHan

> Using a random cropping method, what is the difference between training and testing？ You can read dataset.DatasetTrain and dataset.DatasetVal. When training, we crop the input to 256*256 randomly because...

> disp to depth with min and max depth using this code may be helpful def disp_to_depth(disp, min_depth, max_depth):     """Convert network's sigmoid output into depth prediction     The formula for this...

> I have the same question. The inverse depth output is between 900 and 10000. Is the problem resolved? Hi. I convert the output to depth map by this way....

> @isJHan Thanks! Today I found a bug in this procedure. When I infer on another dataset, the output can be negative or 0. So there will be a bias...

> Now I also add a bias and a scale to the output like this (but not to [0, 1]): > > https://github.com/KU-CVLAB/DaRF/blob/47b2d1a23d13f0d149e55cf8fd2195ec42093d1e/plenoxels/models/dpt_depth.py#L87C18-L87C18 Thanks. But how can we get alpha...

> Inference code like [this](https://github.com/nianticlabs/monodepth2/blob/master/depth_prediction_example.ipynb) would be very much appreciated. Hi, I'm a beginner in DL and there is a question. Whether normalization like (data-avg)/variance is required during inference? I...

You can use `cmake /path/to/Ceres -DUSE_CUDA=false` to disable CUDA support.