I am trying to create an ANN Deep Learning model with PyTorch, and separated functions for calculate loss, and evaluate the model on the validation set. I am having an error RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn.
my code is :
model = MNISTModel()
def accuracy(outputs, labels):
_, preds = torch.max(outputs, dim=1)
return torch.sum(preds == labels).item() / len(preds)
def loss_batch(model, loss_fn, x, y, opt = None, metric = None):
x = Variable(x).cuda()
y = Variable(y.cuda())
preds = model(x)
loss = loss_fn(preds, y)
if opt is not None :
loss.backward()
opt.step()
opt.zero_grad()
metric_result = None
if metric is not None:
metric_result = metric(preds, y)
return loss.item(), len(x), metric_result
def val_evaluate(model, loss_fn, val_loader, metric = None):
with torch.no_grad():
results = [loss_batch(model, loss_fn, x, y, metric) for x,y in val_loader]
losses, nums, metrics = zip(*results)
total = np.sum(nums)
# Avg. loss across batches
avg_loss = np.sum(np.multiply(losses, nums)) / total
avg_metric = None
if metric is not None:
# Avg. of metric across batches
avg_metric = np.sum(np.multiply(metrics, nums)) / total
return avg_loss, total, avg_metric
def fit(epochs, lr, model, loss_fn, train_dl,
valid_dl, metric=None, opt_fn=None):
losses, metrics = [], []
# Instantiate the optimizer
if opt_fn is None: opt_fn = torch.optim.SGD
opt = torch.optim.SGD(model.parameters(), lr=lr)
for epoch in range(epochs):
# Training
for xb,yb in train_dl:
loss,_,_ = loss_batch(model, loss_fn, Variable(xb), Variable(yb), opt)
# Evaluation
result = val_evaluate(model, loss_fn, valid_dl, metric)
val_loss, total, val_metric = result
# Record the loss & metric
losses.append(val_loss)
metrics.append(val_metric)
# Print progress
if metric is None:
print('Epoch [{}/{}], Loss: {:.4f}'
.format(epoch+1, epochs, val_loss))
else:
print('Epoch [{}/{}], Loss: {:.4f}, {}: {:.4f}'
.format(epoch+1, epochs, val_loss,
metric.__name__, val_metric))
return losses, metrics
losses1, metrics1 = fit(5, 0.5, model, nn.CrossEntropyLoss(),
train_loader, val_loader, accuracy)
By comparing it to actual correct code, I found that
whenever I am giving metric = metric in val_evaluate function in the line to get ‘Results’, I am no longer getting this error. But whenever I am passing only metric, this error comes out :
RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn.
but, the accuracy metric has no relation with grad_fn, then why this error is coming?
