RuntimeError: index out of range at /pytorch/aten/src/TH/generic/THTensorEvenMoreMath.cpp:191 about deepfm_with_pytorch HOT 25 OPEN

the same problem~

I had an issue with the embeddings I fixed it initializing the embedding layer with the right size which is the size of the vocabulary I am using.

when creating your Encoder/Model:

self.embed = nn.Embedding(vocab_size, embed_size)
I was using a smaller number than my actual vocab_size thus resulting in an error.

from deepfm_with_pytorch.

Hi, try to inspect the size of your vocabulary , if using the vocab_size in the Embedding layer initialization, try to add +1 to it like -> self.embed = nn.Embedding(vocab_size+1, embed_size)

from deepfm_with_pytorch.

Did anyone get the solution? I'm stuck! just wanted to confirm what vocab_size here means. Does it mean the length of the tokenized words set?

from deepfm_with_pytorch.

It happened to me when I had out-of-vocabulary words which were assigned a -1 value, and also it happens when you set the vocab-size to a smaller value than the size of the vocabulary + 1

from deepfm_with_pytorch.

Hey guys, I had the same problem. In my case, what happened was that I was presenting the Input (X) and the Output (Y) to the model with len(X) != len(Y) due to an error in a third-party library.

Best regards and good luck!

from deepfm_with_pytorch.

Hi, try to inspect the size of your vocabulary , if using the vocab_size in the Embedding layer initialization, try to add +1 to it like -> self.embed = nn.Embedding(vocab_size+1, embed_size)

Hi, this works. But would you mind providing an explanation for this?

I guess it was a bug, which is now fixed by @chenxijun1029 .
What I remember is that the error is because embedding_dim must be equal to the vocab size, but when initializing the embedding layer with len(voca_size) it somehow subtracts 1.

from deepfm_with_pytorch.

hi~
anybody know how to fix this issue?

thanks!

from deepfm_with_pytorch.

the same problem~

from deepfm_with_pytorch.

the same problem~

from deepfm_with_pytorch.

the same problem~

from deepfm_with_pytorch.

same problem

from deepfm_with_pytorch.

Same issue when using flair0.4.1, pythorch1.1.0 and BertEmbeddings on 2 x NVIDIA Tesla P100

from deepfm_with_pytorch.

the same problem

from deepfm_with_pytorch.

the same problem

from deepfm_with_pytorch.

same issue

from deepfm_with_pytorch.

hi, is anybody fix the problem?

from deepfm_with_pytorch.

we have the same problem using LASER bi-LSTM model with PyTorch 1.0 / Python 3.7
https://github.com/facebookresearch/LASER

from deepfm_with_pytorch.

Sorry for answering so late!
I think I've fixed this bug. The main reason is that I accumulated offset when iterate feature size in data preprocess, so index of categorial feature is out of embedding size. Please refer to the update in dataPreprocess.py.
Also, I've found that I should set the index of coutinous feature as 0, and the value of coutinous feature as its original value instead of 1. Refer to the update of dataset.py for more details.
Thanks for your attention.

from deepfm_with_pytorch.

@chenxijun1029 in which version this has been fixed? Thank you.

from deepfm_with_pytorch.

the same problem~

I had an issue with the embeddings I fixed it initializing the embedding layer with the right size which is the size of the vocabulary I am using.

when creating your Encoder/Model:

self.embed = nn.Embedding(vocab_size, embed_size)
I was using a smaller number than my actual vocab_size thus resulting in an error.

Hi. I too resolved my issue by fixing what @mcszn suggested.

from deepfm_with_pytorch.

Hi, try to inspect the size of your vocabulary , if using the vocab_size in the Embedding layer initialization, try to add +1 to it like -> self.embed = nn.Embedding(vocab_size+1, embed_size)

Hi, this works. But would you mind providing an explanation for this?

from deepfm_with_pytorch.

Hi, try to inspect the size of your vocabulary , if using the vocab_size in the Embedding layer initialization, try to add +1 to it like -> self.embed = nn.Embedding(vocab_size+1, embed_size)

Hi, this works. But would you mind providing an explanation for this?

I guess it was a bug, which is now fixed by @chenxijun1029 .
What I remember is that the error is because embedding_dim must be equal to the vocab size, but when initializing the embedding layer with len(voca_size) it somehow subtracts 1.

got it. thanks very much.

from deepfm_with_pytorch.

same issue

from deepfm_with_pytorch.

Hi, try to inspect the size of your vocabulary , if using the vocab_size in the Embedding layer initialization, try to add +1 to it like -> self.embed = nn.Embedding(vocab_size+1, embed_size)

Why +1 will solve the problem,The initialization of embedding should not be used vocab_size rather than vocab_size+1?

from deepfm_with_pytorch.

I have the same issue. See DeepFM_with_PyTorch/data/dataset.py Row7 : continous_features = 13.
Change the value for your dataset. You can have a correct result.

from deepfm_with_pytorch.