The input resolution seems to have a big impact on the model about glpdepth HOT 8 OPEN

Hello, when I was doing the experiment, there was always a gap between the experimental results and the author's results. How did you do this experiment

from glpdepth.

Hello, when I was doing the experiment, there was always a gap between the experimental results and the author's results. How did you do this experiment

I just delete the RandomCrop

from glpdepth.

from glpdepth.

Thank you for your generous answer. It is very helpful to me. Thank you again

from glpdepth.

Have you tried fine-tuning experiments on any other datasets, such as DIODE?

from glpdepth.

I recently tried to reproduce this model and found the same situation as you. I was wondering how you analyzed and concluded that random clipping needed to be removed to bridge the gap between the two

from glpdepth.

Have you tried fine-tuning experiments on any other datasets, such as DIODE?

Sorry for my late reply. I have not fine-tuned this model on other datasets. However, I used the GLPDepth model with 224x224 input size to inference my real scene, and I found the visualization to be very nice. This will mean that GLPDepth has a certain generalization.

from glpdepth.

I recently tried to reproduce this model and found the same situation as you. I was wondering how you analyzed and concluded that random clipping needed to be removed to bridge the gap between the two

I am not very clear, because I have done a lot of experiments, and I found that the data enhancement method of crop will reduce the accuracy of my model, whether it is RandomCrop or CenterCrop.

from glpdepth.