Low time effiency when run cnn on mnist-traning only with CPU

I try to use the following command to train the CNN model with mnist-training example. It works well when training linear and mlp model, but when I config it to train the CNN model, it needs approximately 1hr30mins per epoch. I think it may be abnormal.

`cargo run --example mnist-training --features="candle-datasets" cnn --epochs=5 --save=cnn.safetensors`

Can you please try it?

Start by running the reported `cargo run --example mnist-training --features="candle-datasets" cnn --epochs=5 --save=cnn.safetensors` command on CPU and compare its epoch time with the linear and MLP modes. Done means identifying whether the CNN timing is abnormal and documenting or addressing the cause, with reproducible timing details.

Written by the indexing model from the issue text.