def do_inference(args):
prepare_output_path(args.output_dir, args.overwrite_output_dir)
device, n_gpus = setup_backend(args.no_cuda)
args.task_name = args.task_name.lower()
task = get_glue_task(args.task_name, data_dir=args.data_dir)
args.batch_size = args.per_gpu_eval_batch_size * max(1, n_gpus)
classifier = TransformerSequenceClassifier.load_model(
model_path=args.model_path,
model_type=args.model_type,
task_type=task.task_type,
metric_fn=get_metric_fn(task.name),
do_lower_case=args.do_lower_case,
load_quantized=args.load_quantized_model,
)
classifier.to(device, n_gpus)
examples = task.get_dev_examples(
) if args.evaluate else task.get_test_examples()
preds = classifier.inference(examples,
args.max_seq_length,
args.batch_size,
evaluate=args.evaluate)
with io.open(os.path.join(args.output_dir, "output.txt"),
"w",
encoding="utf-8") as fw:
for p in preds:
fw.write("{}\n".format(p))
def do_inference(args):
prepare_output_path(args.output_dir, args.overwrite_output_dir)
device, n_gpus = setup_backend(args.no_cuda)
args.task_name = args.task_name.lower()
task = get_glue_task(args.task_name, data_dir=args.data_dir)
args.batch_size = args.per_gpu_eval_batch_size * max(1, n_gpus)
classifier = TransformerSequenceClassifier.load_model(
model_path=args.model_path, model_type=args.model_type)
classifier.to(device, n_gpus)
preds = classifier.inference(task.get_test_examples(), args.batch_size)
with io.open(os.path.join(args.output_dir, "output.txt"),
"w",
encoding="utf-8") as fw:
for p in preds:
fw.write("{}\n".format(p))