How to run on GPU?

[ZhouRongqi]

Hello Dear Author, Recently when I run your code, it works fine on CPU but once I switch to GPU I start getting errors. For example, "Parameter 'sequential0_conv0_weight' has not been initialized yet because initialisation was deferred.
Actual initialization happens during the first forward pass. Please pass one batch of data through the network before accessing Parameters.
You can also avoid deferred initialization by specifying in_units, num_features, etc., for network lay
ers."
I hope you can tell me how to run your code correctly on the GPU!Thank you!

[ZhouRongqi]

Hi Dear Author, After my tweaks, the code finally works up on GPU, but why the model doesn't converge? It feels as if no computation is performed?