:bug: issue concerning the interaction of MC-Dropout and the other methods

[haofanwang]

I'm running following command on cifar10

python3 resnet.py --version mimo --arch 18 --accelerator gpu --device 1 --benchmark True --max_epochs 75 --precision 16 --root "./data/" --num_estimators 4

but it raises error RuntimeError: The size of tensor a (512) must match the size of tensor b (128) at non-singleton dimension 0. I dive into the code and find that it may be related to this line, should we remove it? @o-laurent Could you help with this?

Edit by maintainer:

• Either add an "mc_dropout" parameter to the CLI or to the models (we could have dropout during training + MIMO or else, especially for wideresnets)

[o-laurent]

Hi! Thanks a lot for the heads-up! I've just issued a temporary fix on dev. To access it, just git checkout dev. I'll update your comment to explain what happens (interaction with dropout) that we must solve before merging #70. In the meantime, combining MIMO and dropout will lead to the same error. Please do not hesitate if you have any other troubles or questions!

[haofanwang]

It really helps, thanks for your quick reply.