def inference_no_args(
data: TensorDataset,
loader: DataLoader,
logger: Logger,
model: BertForSequenceClassification,
batch_size: int,
) -> List[float]:
device = torch.device('cuda:0') if torch.cuda.is_available() else torch.device('cpu')
predictions = []
states = []
logger.info("***** Running inference {} *****".format(""))
logger.info(" Num examples = %d", len(data))
logger.info(" Batch size = %d", batch_size)
model.to(device)
model.eval()
for batch in tqdm(loader, desc="Inference"):
batch = tuple(t.to(device) for t in batch)
logits, state = model.forward(input_ids=batch[0], attention_mask=batch[1], token_type_ids=batch[2],
output_hidden_states=True)
predictions.extend(logits.cpu())
states.extend(state[-1][:, 0, :].cpu())
return predictions, states
'num_workers': 0}
training_loader = DataLoader(training_set, **params)
testing_loader = DataLoader(testing_set, **params)
loss_function = nn.CrossEntropyLoss()
learning_rate = 2e-05
optimizer = optim.Adam(params = model.parameters(), lr=learning_rate)
if torch.cuda.is_available():
print("GPU is AVAILABLE!")
model = model.cuda()
ids, tokens, labels = next(iter(training_loader)) # iterated one element at a time
ids.shape, tokens.shape, labels
if model_type == 'bert':
print(model_type)
out = model.forward(ids.cuda())[0]
print(loss_function(out, labels.cuda()))
print(out.shape)
"""**Training the model**"""
def train(model, epochs):
max_epochs = epochs
model = model.train()
for epoch in tqdm_notebook(range(max_epochs)):
print("EPOCH -- {}".format(epoch))
correct = 0
total = 0
for i, (ids, tokens, labels) in enumerate(training_loader):
optimizer.zero_grad()
