facebookresearch / moco

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
MIT License
4.82k stars 794 forks source link

about change the base model #124

Open zhou-rui1 opened 2 years ago

zhou-rui1 commented 2 years ago

Hi, I am trying to adopt another model as base-encoder, but it seems wrong with the type of q, it reminds that I am using tuple other than the original type torch tensor... image image

I just wondering if the model can be changed...or the problem is my model? the following is the forward part of my model: image

with regards, I would be really appreciate if you could give me some advice!