sanny
sanny
@happsky see [issue 4884](https://github.com/pytorch/pytorch/issues/4884). Increasing input size or adapting the network architecture seems to fix this as Kernel size in later layers can get too large for the corresponding feature...
Same issue here. Deleting the `src_norm.t() + ` part worked for me.
thanks for the PR!
> Hi, on another note, would it be possible to introduce an # Education section? We run School of Solana and we would like to highlight it too, if no...