Never mind, I think I am going to go ahead with passing the training set as
the validation set for now.
On Tuesday, September 6, 2016 at 8:17:02 PM UTC+5:30, Mallika Agarwal wrote:
>
> Hello,
>
> I have a dataset divided into just a train and test set. Is there a way I
> can skip the "validation" part?
>
> Could someone guide me on how to? Because the part where the validation
> score is checked, I can't simply remove that, can I?
>
> if (iter + 1) % validation_frequency == 0:
>
> # compute zero-one loss on validation set
> validation_losses = [validate_model(i) for i
> in range(n_valid_batches)]
> this_validation_loss = numpy.mean(validation_losses)
> print('epoch %i, minibatch %i/%i, validation error %f %%' %
> (epoch, minibatch_index + 1, n_train_batches,
> this_validation_loss * 100.))
>
> # if we got the best validation score until now
> if this_validation_loss < best_validation_loss:
>
> #improve patience if loss improvement is good enough
> if this_validation_loss < best_validation_loss * \
> improvement_threshold:
> patience = max(patience, iter * patience_increase)
>
> # save best validation score and iteration number
> best_validation_loss = this_validation_loss
> best_iter = iter
>
> # test it on the test set
> test_losses = [
> test_model(i)
> for i in range(n_test_batches)
> ]
> test_score = numpy.mean(test_losses)
> print((' epoch %i, minibatch %i/%i, test error of '
> 'best model %f %%') %
> (epoch, minibatch_index + 1, n_train_batches,
> test_score * 100.))
>
> This is from convolutional_mlp.py.
>
> Thanks in anticipation!
>
--
---
You received this message because you are subscribed to the Google Groups
"theano-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
