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

Is this due to my mishandling of my data in this project? #23

Open
hothot9532 opened this issue Apr 17, 2024 · 4 comments
Open

Is this due to my mishandling of my data in this project? #23

hothot9532 opened this issue Apr 17, 2024 · 4 comments

Comments

@hothot9532
Copy link

An error occurs when I perform the following steps:
5cbff121304e80da9ef2f6aa0c5adac6
I did this for my dataset, using the test section of VITON-HD, where "image" corresponds to "model", "cloth" corresponds to "product", and "openpose_json" corresponds to "pose":
34a73c54d86d7739407e88f416866a54
1a6be900acadc6b390aa99d4ac38ac8a
0cd24f4e4a5554c889246e30d60b62bb
09f2e8c935e337f238b4073c62c5c6a6

@hothot9532
Copy link
Author

There's a picture missing:
1db193262d68975bfc25157a689774a6

@sahilshukla3003
Copy link

This might be due incorrect preprocessing , follow each step and verify results after each step , currently sleeve_classifier is unable to find any data and got the num samples 0

@hothot9532
Copy link
Author

This might be due incorrect preprocessing , follow each step and verify results after each step , currently sleeve_classifier is unable to find any data and got the num samples 0

I found that the official raw_data was able to execute normally, but the VITON_HD_top that I created by myself would report such an error. I repeatedly made sure that my previous preprocessing steps were correct, but finally I would get stuck in this step

@hothot9532
Copy link
Author

This might be due incorrect preprocessing , follow each step and verify results after each step , currently sleeve_classifier is unable to find any data and got the num samples 0

I found that the official raw_data was able to execute normally, but the VITON_HD_top that I created by myself would report such an error. I repeatedly made sure that my previous preprocessing steps were correct, but finally I would get stuck in this step

Pose screening, semantic screening, mask generation, and several steps of pre-processing before this should be the same as the results in the official men_top and men_knitwear folders. I don't know why I will report errors when I create my own data set

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

2 participants