Galin Wu

Here's one: ```python import torch import matchzoo as mz from anmm_train import * test_pack = mz.datasets.wiki_qa.load_data('test', task=ranking_task) test_processed = preprocessor.transform(test_pack, verbose=0) testset = mz.dataloader.Dataset( data_pack=test_processed, mode='point', batch_size=32 ) testloader =...

But thank goodness in raw cases people will expand `n_tag` so this problem doesn't go explicit.