Siamese-LSTM
Siamese-LSTM copied to clipboard
likejazz
Siamese LSTM for evaluating semantic similarity between sentences of the Quora Question Pairs Dataset.
In the prediction make_w2v_embeddings creates a new vector for each sentence. So numbers are not consistent with the prediction. It should be same with the training data. For example when...
Y = train_df['is_duplicate'] I do not understand this part of the code in train.py
Hi, I got 0 accuracy by using the project. How do you get the accuracy result by using the top 20 test question pair? Because those test question pairs are...
InternalError: Blas GEMM launch failed : a.shape=(1024, 64), b.shape=(64, 50), m=1024, n=50, k=64
