1 year ago

#6681

test-img

Roi Kremer

RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)`

I'm trying to extract feathers from BertTopic model and I'm using jupyter notebook. The first feature is sentiment analysis and it's done by following code: df-DataFrame, df["title_selftext"] - this data frame column contain a text (str)

  def get_sentiment(model, tokenizer, data):
     inputs = tokenizer(data, padding=True, return_tensors="pt")
     outputs = model(**inputs.to(device))
     return torch.nn.functional.softmax(outputs.logits.detach())

 res = []
 for txt in tqdm(batches(df["title_selftext"],20), total=len(df)//32):
    **res.append(get_sentiment(model,tokenizer, list(txt)))** 

when im trying to append the get_sentiment output i for this error: RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)

please help me to solve this error Thank you

python

jupyter

sentiment-analysis

topic-modeling

cuda-gdb

0 Answers

Your Answer

Accepted video resources