IndexError: When performing advanced indexing the indexing objects must be LongTensors or convertible to LongTensors

[Jayashree-Pougajendy]

Hi,
I am getting the foll. error on training convcap using torch 0.2.0_3 and torchvision 0.1.9. Kindly suggest how to resolve.
Traceback (most recent call last):
File "main.py", line 89, in
main()
File "main.py", line 72, in main
train(args)
File "/home/js/convcap/train.py", line 126, in train
loss = F.cross_entropy(wordact_t[maskids, ...],
File "/home/js/anaconda3/envs/env_con/lib/python3.5/site-packages/torch/autograd/variable.py", line 76, in getitem
return Index.apply(self, key)
File "/home/js/anaconda3/envs/env_con/lib/python3.5/site-packages/torch/autograd/_functions/tensor.py", line 16, in forward
result = i.index(ctx.index)
IndexError: When performing advanced indexing the indexing objects must be LongTensors or convertible to LongTensors