UniDepth

UniDepth copied to clipboard

encountered an error while executing the demo

3

``` (Unidepth) hygx@DESKTOP-47Q8A9V:~/code/UniDepth$ python ./scripts/demo.py Triton is not available, some optimizations will not be enabled. This is just a warning: triton is not available Torch version: 2.2.0+cu118 Instantiate: dinov2_vitl14 Traceback...

JV-X

How to setup the environment and use the model on Google colab

mohamedaissaoui2000

 no need to normalize a normalized tensor

zylo117

I want to run this script on grayscale image

1

Abhinav-974

Blockish artifacts in depth

1

Hello Great Work! I am trying to use Unidepth as inference. However, the depth map that I am obtaining is very blockish. Perhaps, this has to do with patch tokenization?...

Davidyao99

The depth color is opposite to the sample given

4

` import numpy as np from PIL import Image import torch import h5py import os import numpy as np import cv2 device = torch.device("cuda" if torch.cuda.is_available() else "cpu") model =...

wrx1990

why use exp?

3

Thank you for your work! I found in your code that your predictions for fx and fy as well as depth are done with .exp(), I want to understand why...

yamoomd

is there any update on unidepth v2?

2

zylo117

encountered an error while executing the demo

16

python ./scripts/demo.py Torch version: 2.2.0+cu121 Downloading: "https://github.com/lpiccinelli-eth/unidepth/zipball/main" to /home/feol/.cache/torch/hub/main.zip Instantiate: dinov2_vitl14 UniDepthV1_ViTL14 is loaded with: missing keys: ['pixel_encoder.register_tokens'] additional keys: [] Segmentation fault (core dumped)

feolcn

how to train

2

I have my own dataset and want to train this model on my own dataset but i didn‘t see the detail of how to train

Ericchen328