IndexError: only integers, slices (`:`), ellipsis (`...`), numpy.newaxis (`None`) and integer or boolean arrays are valid indices

[chirstinaFan]

I have some trouble running the train.py, and I guess the problem is here:
def getitem(self, index):
# handle the image redundancy
img_id = index/self.im_div
image = torch.Tensor(self.images[img_id])
caption = self.captions[index]
vocab = self.vocab
And the img_id is not an integer
could you find this problem?

[fartashf]

@chirstinaFan if you fixed the issue, can you give the details for the fix? Thank you.

[chirstinaFan]

img_id = int(index/self.im_div)

And I find another problem. when I try to build vocabulary，there are many mistakes.can you tell me how do you build your vocabulary?

[fartashf]

Interesting. Thanks for reporting the fix.

Can you open another issue for the errors in building the vocabulary and give more details? Thanks.