| thon | |
| from transformers import pipeline | |
| from transformers.pipelines.pt_utils import KeyDataset | |
| import datasets | |
| dataset = datasets.load_dataset("imdb", name="plain_text", split="unsupervised") | |
| pipe = pipeline("text-classification", device=0) | |
| for out in pipe(KeyDataset(dataset, "text"), batch_size=8, truncation="only_first"): | |
| print(out) | |
| # [{'label': 'POSITIVE', 'score': 0.9998743534088135}] | |
| # Exactly the same output as before, but the content are passed | |
| # as batches to the model | |
| However, this is not automatically a win for performance. |