I have trained a model using torchtext for the data processing e.g.
TEXT = data.Field()
LABELS = data.Field()
train, val, test = data.TabularDataset.splits(
path='/data/pos_wsj/pos_wsj', train='_train.tsv',
validation='_dev.tsv', test='_test.tsv', format='tsv',
fields=[('text', TEXT), ('labels', LABELS)])
train_iter, val_iter, test_iter = data.BucketIterator.splits(
(train, val, test), batch_sizes=(16, 256, 256),
sort_key=lambda x: len(x.text), device=0)
TEXT.build_vocab(train)
LABELS.build_vocab(train)
Now I have documents coming in one at a time that will arrive in-memory to Python. I would like to use the same tokenization and numericalization to process these documents and then pass to my model to make a prediction, e.g.
new_doc = "hello world"
X = TEXT.process(new_doc)
pred = model(X)
This doesn’t work - any ideas on how I can process this in-memory text?