Hello,
I am trying to train a siamese network with Binary Cross Entropy.
I have the following error in train_epoch:
y_true_2[range(y_true_2.shape[0]), y_true.long()] = 1
IndexError: index -9223372036854775808 is out of bounds for dimension 1 with size 2
Following is the code snippet for reference:
def train_epoch(train_loader, model, loss_fn, optimizer, cuda, log_interval, metrics, step=None):
for metric in metrics:
metric.reset()
model.train()
losses = []
total_loss = 0
for batch_idx, ((x0, x1), y) in enumerate(train_loader):
y_true = y
x0, x1, y_true = x0.cuda(), x1.cuda(), y.cuda()
optimizer.zero_grad()
output1, output2 = model(x0, x1)
#print('output1 is:', output1)
#print('output2 is:', output2)
#print('y_true is', y_true)
'''Distance metric - PairwiseDistance'''
#p_dist = torch.nn.PairwiseDistance(keepdim=True)
p_dist = torch.nn.CosineSimilarity(dim=1, eps=1e-08)
dy = p_dist(output1, output2)
# dy = torch.reshape(dy, (2,1))
# print('dy_shape after squeeze', dy.size())
dy = torch.nan_to_num(dy)
# y_true = torch.reshape(y_true, (2,))
# print('y_true_shape after squeeze', y_true.size())
y_true = torch.nan_to_num(y_true)
# print('dy is:', dy)
'''2 lines indicated the normalization of dy to 0 and 1 by dividing it with max value'''
maximum_dy = torch.max(dy)
maximum_dy = torch.nan_to_num(maximum_dy)
dy = dy / maximum_dy
# print('dy after max is', dy)
# print('y_true is', y_true)
maximum_y_true = torch.max(y_true)
maximum_y_true = torch.nan_to_num(maximum_y_true)
# print('maximum y_true is', maximum_y_true)
y_true = y_true / maximum_y_true
# print(' y_true after max is', y_true)
# print('dy_shape:', dy.size(), 'y_true_shape:', y_true.size())
# print('dy_shape after squeeze', dy.size())
#dy = torch.squeeze(dy, 1)
input_dy = torch.empty(dy.size(0), 2)
#print(input_dy )
input_dy[:, 0] = 1 - dy
input_dy[:, 1] = dy
# print('Output for loss function', input_dy)
y_true_2 = torch.zeros(dy.size(0), 2)
#print(y_true_2)
#y_true_2 = torch.nan_to_num(y_true_2)
y_true_2[range(y_true_2.shape[0]), y_true.long()] = 1
#y_true_2 = torch.nan_to_num(y_true_2)
m = nn.Sigmoid()
loss = loss_fn(m(input_dy), y_true_2)
loss.backward()
optimizer.step()
losses.append(loss.item())
total_loss += loss.item()
input_dy_metric = torch.round(input_dy)
for metric in metrics:
metric(input_dy_metric, y_true_2)
metric.total += y_true_2.shape[0]
if batch_idx % log_interval == 0:
message = 'Train: [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
batch_idx, len(train_loader),
100. * batch_idx / len(train_loader), np.mean(losses))
for metric in metrics:
message += '\t{}: {}'.format(metric.name(), metric.value())
#print(message)
losses = []
total_loss /= (batch_idx + 1)
return total_loss, metrics
Can anyone please help here?
Thanks in advance