thunlp / LLaVA-UHD

LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images
303 stars 15 forks source link

Runtime error #12

Open Zhangjy1998 opened 5 months ago

Zhangjy1998 commented 5 months ago

During the fine-tune period,I met this error causing task fail: RuntimeError: Given groups=1, weight of size [1024, 3, 14, 14], expected input[4, 9, 336, 336] to have 3 channels, but got 9 channels instead.

wendychina commented 5 months ago

I'm meeting the same runtime error,have you solved the problem?