Using custom image to inference

CyberAgentAILab / RALF

[CVPR24 Oral] Official repository for RALF: Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation

https://arxiv.org/abs/2311.13602

Apache License 2.0

96 stars 1 forks source link

Using custom image to inference #17

Open HenryQUQ opened 2 months ago

HenryQUQ commented 2 months ago

Hello, I am trying to modify inference_single_data.py file for the custom image inference. However, I saw the data in the test split has label, center_x, ... data, which my custom image does not have. Also, I saw there is 'label' and 'mask' items in the "cond", Line 356, but for my own image, I don't have it. Hope you can solve my question.

UdonDa commented 2 months ago

Thank you for attracting our work. We do not assume that a test image has such annotations since we use an “unannotated” split in our evaluation. We believe that you could achieve what you want to do. Please debug your scenario by yourself.

gsrujana commented 2 months ago

@HenryQUQ were you able to acheive this?