A Problem About Embed

[pydxflwb]

loader size 1
training model
Traceback (most recent call last):
File "EANN.py", line 558, in
main(args)
File "EANN.py", line 317, in main
class_outputs, domain_outputs = model(train_text, train_image, train_mask)
File "C:\Users\15821\anaconda3\envs\python36\lib\site-packages\torch\nn\modules\module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "EANN.py", line 156, in forward
text = self.embed(text)
File "C:\Users\15821\anaconda3\envs\python36\lib\site-packages\torch\nn\modules\module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "C:\Users\15821\anaconda3\envs\python36\lib\site-packages\torch\nn\modules\sparse.py", line 114, in forward
self.norm_type, self.scale_grad_by_freq, self.sparse)
File "C:\Users\15821\anaconda3\envs\python36\lib\site-packages\torch\nn\functional.py", line 1724, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
RuntimeError: Expected tensor for argument #1 'indices' to have scalar type Long; but got torch.cuda.IntTensor instead (while checking arguments for embedding)

Thanks for your work! And I'm confused what type of data the "text" data should be converted into.