convs2s_iterator.py

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
BATCH_SIZE = 128 ### Hyperparameter

"""
Defines an iterator that batches examples of similar lengths together thereby minimizes the padding per batch.
"""
train_iterator, valid_iterator, test_iterator = BucketIterator.splits(
    (train_data, valid_data, test_data), 
     batch_size = BATCH_SIZE,
     device = device)

### Single sample from train_iterator
sample_from_iterator = next(iter(train_iterator))
print(sample_from_iterator)
print("Fields in the iterator", sample_from_iterator.fields)
print("Shape of ", sample_from_iterator.src.shape, sample_from_iterator.trg.shape)

#### Output
"""
[torchtext.data.batch.Batch of size 128 from MULTI30K]
	[.src]:[torch.cuda.LongTensor of size 128x33 (GPU 0)]
	[.trg]:[torch.cuda.LongTensor of size 128x35 (GPU 0)]
Fields in the iterator dict_keys(['src', 'trg'])
Shape of  torch.Size([128, 33]) torch.Size([128, 35])
"""