When processing a grayscale image with different width and height the following error will occur.
Exception in TokenizerManager:
Traceback (most recent call last):
File "/home/gcpuser/sglang/python/sglang/srt/managers/tokenizer_manager.py", line 61, in get_pixel_values
image = expand2square(
File "/home/gcpuser/sglang/python/sglang/srt/mm_utils.py", line 167, in expand2square
result = Image.new(pil_img.mode, (width, width), background_color)
File "/opt/conda/envs/sglang_flashinfer/lib/python3.9/site-packages/PIL/Image.py", line 2941, in new
return im._new(core.fill(mode, size, color))
TypeError: color must be int or single-element tupleThe error originates here and it fails because PIL won't the background consisting of 3 values to the new image with L mode.
So far I only encountered this for grayscale images, perhaps one way to solve it would be to convert these images to RGB before resizing them?
When processing a grayscale image with different width and height the following error will occur.
The error originates here and it fails because PIL won't the background consisting of 3 values to the new image with
Lmode.So far I only encountered this for grayscale images, perhaps one way to solve it would be to convert these images to
RGBbefore resizing them?