Dropout(): аргумент «вход» (позиция 1) должен быть тензорным, а не str BERT. ⇐ Python

[Anonymous]

Я пытался запустить несколько эпох, чтобы обучить свою модель анализа настроений, в самом последнем отрывке эпохи остановились из-за ошибки в заголовке. Коды прилагаю здесь:
Классификатор настроений:

Код: Выделить всё

# Build the Sentiment Classifier class
class SentimentClassifier(nn.Module):

# Constructor class
def __init__(self, n_classes):
super(SentimentClassifier, self).__init__()
self.bert = BertModel.from_pretrained(MODEL_NAME)
self.drop = nn.Dropout(p=0.3)
self.out = nn.Linear(self.bert.config.hidden_size, n_classes)

# Forward propagaion class
def forward(self, input_ids, attention_mask):
_, pooled_output = self.bert(
input_ids=input_ids,
attention_mask=attention_mask
)
#  Add a dropout layer
output = self.drop(bertOutput['pooler_output'])
return self.out(output)

Итерации:

Код: Выделить всё

# Number of iterations
EPOCHS = 10

# Optimizer Adam
optimizer = AdamW(model.parameters(), lr=2e-5, correct_bias=False)

total_steps = len(train_data_loader) * EPOCHS

scheduler = get_linear_schedule_with_warmup(
optimizer,
num_warmup_steps=0,
num_training_steps=total_steps
)

# Set the loss function
loss_fn = nn.CrossEntropyLoss().to(device)

оценка (при возникновении проблемы):

Код: Выделить всё

def eval_model(model, data_loader, loss_fn, device, n_examples):
model = model.eval()

losses = []
correct_predictions = 0

with torch.no_grad():
for d in data_loader:
input_ids = d["input_ids"].to(device)
attention_mask = d["attention_mask"].to(device)
targets = d["targets"].to(device)

# Get model ouptuts
outputs = model(
input_ids=input_ids,
attention_mask=attention_mask
)

_, preds = torch.max(outputs, dim=1)
loss = loss_fn(outputs, targets)

correct_predictions += torch.sum(preds == targets)
losses.append(loss.item())

return correct_predictions.double() / n_examples, np.mean(losses)

и, наконец, сама ошибка:

Код: Выделить всё

%%time

history = defaultdict(list)
best_accuracy = 0

for epoch in range(EPOCHS):

# Show details
print(f"Epoch {epoch + 1}/{EPOCHS}")
print("-" * 10)

train_acc, train_loss = train_epoch(
model,
train_data_loader,
loss_fn,
optimizer,
device,
scheduler,
len(df_train)
)

print(f"Train loss {train_loss} accuracy {train_acc}")

# Get model performance (accuracy and loss)
val_acc, val_loss = eval_model(
model,
val_data_loader,
loss_fn,
device,
len(df_val)
)

print(f"Val   loss {val_loss} accuracy {val_acc}")
print()

history['train_acc'].append(train_acc)
history['train_loss'].append(train_loss)
history['val_acc'].append(val_acc)
history['val_loss'].append(val_loss)

# If we beat prev performance
if val_acc > best_accuracy:
torch.save(model.state_dict(), 'best_model_state.bin')
best_accuracy = val_acc

Код: Выделить всё

Epoch 1/10
----------
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
 in 

 in train_epoch(model, data_loader, loss_fn, optimizer, device, scheduler, n_examples)
10         targets = d["targets"].to(device)
11
---> 12         outputs = model(
13             input_ids=input_ids,
14             attention_mask=attention_mask

6 frames
/usr/local/lib/python3.10/dist-packages/torch/nn/functional.py in dropout(input, p, training, inplace)
1423         raise ValueError(f"dropout probability has to be between 0 and 1, but got {p}")
1424     return (
-> 1425         _VF.dropout_(input, p, training) if inplace else _VF.dropout(input, p, training)
1426     )
1427

TypeError: dropout(): argument 'input' (position 1) must be Tensor, not str

Я имел в виду трансформаторы

Код: Выделить всё

pip install transformers==3

но ничего.
Любая помощь приветствуется!

Подробнее здесь: https://stackoverflow.com/questions/792 ... bert-issue