lda2vec-pytorch
lda2vec-pytorch copied to clipboard
TropComplique
Topic modeling with word vectors
The code doesn't work with the current version of libraries, due to some API changes. I've updated the code to solve this problem, and fixed the gradient explosion problem too....
I have this error No such file 'model_state.python' , I don't find this file. who can help me plz
i wanted to train this code with my own data stored in mysql database, how do it ?? which module.py will modify ?? help please
Running on GoogleColab with python 3 + GPU: Issue in preprocess.py on line #26 for method nlp(): ``` nlp = spacy.load('en') text = nlp(text, tag=True, parse=False, entity=False) ``` nlp() unknown...
Running on GoogleColab. 'Encounter the problem "IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number".' This solution worked for me: https://github.com/pytorch/pytorch/issues/15585
_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...
I ran all your code successfully. In explore_trained_model.ipynb, I see that you get prediction results for trained documents. However, I want to infer topics distribution for new documents. Please tell...
MY COMPUTER: NVIDIA CUDA 9.0.176 driver Torch-0.3.0 When I run "train.py" ， it always stops at the following interface. Please help me , thank you very much.
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 127, in train neg_loss, dirichlet_loss = model(doc_indices, pivot_words,...