You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
i have the problem in
encoded_docs, decoder, word_counts = preprocess(
docs, nlp, MIN_LENGTH, MIN_COUNTS, MAX_COUNTS
)
i don't know why i have this problem
The text was updated successfully, but these errors were encountered:
i skip the paremeter tag and parse in preprocess.py and run it success
but, while i run the step2 train.py
i have the problem about cuda like this
number of documents: 13109
number of windows: 1063444
number of topics: 25
vocabulary size: 7596
word embedding dim: 50
THCudaCheck FAIL file=/pytorch/aten/src/THC/THCGeneral.cpp line=74 error=30 : unknown error
Traceback (most recent call last):
File "train.py", line 36, in
main()
File "train.py", line 32, in main
save_every=20, grad_clip=5.0
File "../utils/training.py", line 72, in train
weights = torch.FloatTensor(weights).cuda()
RuntimeError: cuda runtime error (30) : unknown error at /pytorch/aten/src/THC/THCGeneral.cpp:74
call_() got an unexpected keyword argument 'tag'
i have the problem in
encoded_docs, decoder, word_counts = preprocess(
docs, nlp, MIN_LENGTH, MIN_COUNTS, MAX_COUNTS
)
i don't know why i have this problem
The text was updated successfully, but these errors were encountered: