You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- Train Qwen2VL model using any config and a dataset that contains images `> image_resolution`
- Images are resized using nearest neighbor interpolation
Nearest neigbor downsampling incurs a large loss in image quality (small lines vanish, see the attached image). Qwen2VL generally uses BICUBIC downsampling instead to circumvent the this problem.
Generally, it would be great if one could directly configure with image_resolution and use the transformers preprocessor that is called after anyway.
The text was updated successfully, but these errors were encountered:
We have fixed it in #7143, thank you for reporting
hiyouga
added
solved
This problem has been already solved
and removed
bug
Something isn't working
pending
This problem is yet to be addressed
labels
Mar 3, 2025
"[Qwen2VL] generally uses BICUBIC downsampling instead to circumvent the this problem." Does that mean Qwen2VL should use BICUBIC? but now it seems Qwen2vl still uses the nearest neighbor in Qwen2vlPlugin._preprocess_image.
Reminder
System Info
Reproduction
Others
Nearest neigbor downsampling incurs a large loss in image quality (small lines vanish, see the attached image). Qwen2VL generally uses BICUBIC downsampling instead to circumvent the this problem.
Generally, it would be great if one could directly configure with
image_resolution
and use thetransformers
preprocessor that is called after anyway.The text was updated successfully, but these errors were encountered: