At training, RuntimeError: The size of tensor a (148) must match the size of tensor b (150) at non-signleton dimesnion 1

wjun0830 / QD-DETR

Official pytorch repository for "QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection" (CVPR 2023 Paper)

https://arxiv.org/abs/2303.13874

Other

199 stars 15 forks source link

At training, RuntimeError: The size of tensor a (148) must match the size of tensor b (150) at non-signleton dimesnion 1 #23

Closed themingcha closed 1 year ago

themingcha commented 1 year ago

hello. When training a model with video_tep, I am getting a RunError when calculating loss with inference.py after 5 epochs (i.e., criterion) because the tensor shape does not fit. These are the latest git files, what could be the problem?

runtime_error_real

Thanks.

**sorry, I address this issue. (i.e. config.py)

PLEASE DELETE THIS ISSUE.**