Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

how to test single picture? #70

Open
eugeneYz opened this issue Nov 22, 2022 · 2 comments
Open

how to test single picture? #70

eugeneYz opened this issue Nov 22, 2022 · 2 comments

Comments

@eugeneYz
Copy link

how can I test one single picture , and get the output of the depth value?

@mexicantexan
Copy link

mexicantexan commented Nov 27, 2022

The way that the owner of this repo has it set up at this time, out of the box you can't just test on one of your images. A "hacky" way to get the depth values is to one of the following:

  1. Copy your image into the corresponding data directory and adjust the test.txt file associated with that directory to only have the name of your image in it. i.e. if you're running binsformer. Copy your image into the data/nyu directory then adjust the nyu_test_.txt to only have your image name in it.
  2. Edit the tools/test.py file directly
  3. point the config file parameter 'data_root' to the directory that contains your image
  4. also check out -> https://github.com/zhyever/Monocular-Depth-Estimation-Toolbox/blob/main/docs/dataset_prepare.md#prepare-datasets to set up your own custom dataset using the steps there

@fanshixiong
Copy link

fanshixiong commented Aug 29, 2023

@mexicantexan Hello, I put the pictures in the nyu dataset directory, and modified the nyu_test file, but the program does not run normally, but the nyu dataset can run normally, is it because of the resolution or what?Thanks.

My data resolution is 3840 * 2160, what needs to be modified?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants