Shows error RuntimeError: Expected tensor for argument #1 'indices' to have scalar type Long; but got CPUIntTensor instead (while checking arguments for embedding) while running train_transe_model.py script #2
Description
Traceback (most recent call last):
File "train_transe_model.py", line 145, in
main()
File "train_transe_model.py", line 140, in main
train(args)
File "train_transe_model.py", line 45, in train
train_loss = model(batch_idxs)
File "C:\Users\hp\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "C:\Users\hp\fld\transe_model.py", line 99, in forward
loss = self.compute_loss(batch_idxs)
File "C:\Users\hp\fld\transe_model.py", line 119, in compute_loss
up_loss, up_embeds = self.neg_loss('user', 'purchase', 'product', user_idxs, product_idxs)
File "C:\Users\hp\fld\transe_model.py", line 188, in neg_loss
relation_vec, relation_bias_embedding, self.num_neg_samples, entity_tail_distrib)
File "C:\Users\hp\fld\transe_model.py", line 209, in kg_neg_loss
entity_head_vec = entity_head_embed(entity_head_idxs) # [batch_size, embed_size]
File "C:\Users\hp\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "C:\Users\hp\Anaconda3\lib\site-packages\torch\nn\modules\sparse.py", line 108, in forward
self.norm_type, self.scale_grad_by_freq, self.sparse)
File "C:\Users\hp\Anaconda3\lib\site-packages\torch\nn\functional.py", line 1076, 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 CPUIntTensor instead (while checking arguments for embedding)