Qiao Jin
Qiao Jin
@kopxiong It makes sense to change the hyperparameters. I've tried your suggestion, but the loss didn't drop to a satisfying level. Have you checked the `y_pred` of the final model?
> This would work except for the pesky issue of the statefulness of the LSTM states. The perplexities for the first batch or two are artificially high until the model...
Thanks. 24GB is suitable for a batch size of 16. Larger batch sizes require larger GPU memories to run.
URLs cannot contain spaces. URL encoding normally replaces a space with a plus (+) sign or with %20.
That might cause parsing issues for the API? If you don't have spaces between words sometimes the service returns nothing.