RuntimeError: Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [1, 1, 3, 336, 336]

dvlab-research / MGM

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

Apache License 2.0

3.22k stars 280 forks source link

Closed plf1996 closed 7 months ago

plf1996 commented 7 months ago

When I generate it using the example image, it tells me that the dimensions are not correct

wcy1122 commented 7 months ago

Hi, the bug is fixed. You can update the latest code and try again.

TGLTommy commented 5 months ago

Hi, the bug is fixed. You can update the latest code and try again.

Hi, where is the code did you updated ?

plf1996 commented 5 months ago

Hi, the bug is fixed. You can update the latest code and try again.

Thank you, I will keep trying