I followed the instructions in https://github.com/sunwei925/SimpleVQAļ¼and tried to use the baseline model to test the videos. I only modified the dist path in test.sh to be the path of a video in this competition, but an error occurred:
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 4 but got size 8 for tensor number 1 in the list.
This error appears to be due to the test video not meeting the input size requirements, but I was unable to see the requirement of input size in Readme. What do I need to do?