Pytorch Error, RuntimeError: expected scalar type Long but found Double

Question

I have run into the following error while training a BERT classifier. The

type(b_input_mask) = type(b_labels) = torch.Tensor      

type(b_labels[i]) = tensor(1., dtype=torch.float64)

type(b_input_masks[i]) = class'torch.Tensor'

What could be the possible data type error here since I have not typecasted any variable to either long or double?

Thanks in advance!

Bugface · Accepted Answer · 2020-06-16 03:07:31Z

2

In a classification task, the data type for input labels should be Long but you assigned them as float64

type(b_labels[i]) = tensor(1., dtype=torch.float64)

=>

type(b_labels[i]) = tensor(1., dtype=torch.long)

answered Jun 16, 2020 at 3:07

Bugface

3132 silver badges7 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

Soumya Ranjan Sahoo Over a year ago

where should I typecast the float type to long type? In the above-attached image, will labels = np.int_(b_input_mask) will do it for me? Note: np.int_ is for long type.

Dishin Goyani · Accepted Answer · 2020-06-16 05:55:19Z

0

You can use torch.Tensor.long to convert tensor to expected long type.

# Here, you can pass parameter like this in your call
..., labels = b_labels.long())

answered Jun 16, 2020 at 5:55

Dishin Goyani

7,7533 gold badges33 silver badges42 bronze badges

Collectives™ on Stack Overflow

Pytorch Error, RuntimeError: expected scalar type Long but found Double

2 Answers 2

1 Comment

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

1 Comment

Comments

Your Answer

Sign up or log in

Post as a guest

Related