Multimodal-Infomax
Multimodal-Infomax copied to clipboard
environment
Hello, I encountered some issues while configuring the environment. It seems that there is an incompatibility between torch 1.7.0 and torchvision 0.4.2. What should I do to resolve this?
I remember torchvision is not imported in the project, so you can firstly try running without it.
I remember torchvision is not imported in the project, so you can firstly try running without it.
Thank you for your reply, the problem has been solved, may I ask how your dataset converts video and voice into pkl files
I remember torchvision is not imported in the project, so you can firstly try running without it.
Thank you for your reply, the problem has been solved, may I ask how your dataset converts video and voice into pkl files
You can extract features according to related papers, and save the results as numpy arrays into the pkl.
file.