Dimo Angelov comments

Results 45 comments of


                                            Dimo Angelov

(0) RESOURCE_EXHAUSTED: OOM when allocating tensor with shape[114389,320] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator Simple allocator [[{{node EncoderDNN/EmbeddingLookup/EmbeddingLookupUnique/GatherV2}}]]

Are you embedding full papers? It looks like a GPU memory problem. Switching to CPU might be a temporary solution.

(0) RESOURCE_EXHAUSTED: OOM when allocating tensor with shape[114389,320] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator Simple allocator [[{{node EncoderDNN/EmbeddingLookup/EmbeddingLookupUnique/GatherV2}}]]

The new top2vec version `1.0.27` has some memory bugfixes as well as an option for document chunking for long documents which could help solve some of these issue. There is...

hierarchical topic reduction KeyError

Great thank you for sharing this! :)

add_documents: The scale between training set and test set

If the subset of your data is a random sample and it is greater than ~10% you should have no problem. The issue is when the topics are formed on...

No argument `embedding_model'

What version of `top2vec` do you have? Also what are you passing `emebdding_model` ?

Top2Vec as an updating model

Depending on the use-case and variability of the corpus you can just use the `add_documents` to add new documents to an existing model. If the corpus is constantly changing you...

import error

I would try creating fresh environment and trying a Top2Vec install there.

ValueError: numpy.ndarray size changed, may indicate binary incompatibility.

What `embedding_model` did you use and during which step did you get this error?

ValueError: numpy.ndarray size changed, may indicate binary incompatibility.

I have no issues with this and I have python 3.8.5 so I don't think that is the issue.

ValueError: numpy.ndarray size changed, may indicate binary incompatibility.

setup.py specifies `python_requires='>=3.6'`