Don't use named tensors in simple-resnet-cifar10 model

[brimoor]

On torch==1.9.0, using the simple-resnet-cifar10 model (the default model for uniqueness, but not for similarity or visualization) produces the following warning:

/Users/Brian/dev/env/fifty3/lib/python3.6/site-packages/torch/nn/functional.py:718: UserWarning:

Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at  ../c10/core/TensorImpl.h:1156.)