Zhenyu Li

No worries. This interface is somehow annoying because it's changing some detailed implementations during updates... It would affect if you change the folder structure. Please leave them there. (as far...

Hi, glad to hear it works. We recommand to use gpu to run patchfusion. It's kind of heavy for cpu

Sorry for the late reply! It might be too hard for the model to predict depth for this figure. It could be out-of-distribution in some sense. Please let me know...

Hi, would you mind to share some results. It might be bugs, but it would be possible that the model is not strong enough to handle the task. Also, it...

Hi, sorry for the late reply. The raw config works for 4gpus training as far as I can remember. Please change the schedule, learning rate, etc, based on your experiment...

Hi guys, I think the PatchFusion is not the best solution for the hr depth estimation. We now have [PatchRefiner](https://arxiv.org/abs/2406.06679) with better performance. I will try to support Depth Anything...

Could you please check 2d87adc9 with `git check 2d87adc9`? I think I provide all initial codes there, including the configs. Checkpoints are provided here: https://huggingface.co/zhyever/PatchFusion/tree/main. You can use the [patchfusion_gta.pt](https://huggingface.co/zhyever/PatchFusion/blob/main/patchfusion_gta.pt)...

Sorry for the late reply. Just came back from one conference. Would you mind to check the shape of the backward loss? Which version of torch are you using? I...

Please check https://github.com/zhyever/Monocular-Depth-Estimation-Toolbox/issues/103 for updated links of binsformer. I cannot provide other models and will not be able to re-train them. Sorry for the inconvenience. It would be great if...