MatchZoo
MatchZoo copied to clipboard
Facilitating the design, comparison and sharing of deep text matching models.
### Describe the bug I've trained and evaluated the DRMM model successfully. When I traied to make predictions in a new dataset, I run this code: ``` test_generator = mz.DataGenerator(data_pack=valid_pack_pp[:10],...
When I called the model according to the hyperparameters given by the model, a problem occurred“ValueError: Layer weight shape (10000, 300) not compatible with provided weight shape (33905, 300)”. So...
### Describe the Question Which paper did the hbmp model come from?
How to pass my own embedding path to the model parameters or possibly the processor? Thank you very much !
### Describe the bug Loading word2vec embedding causes the memory issue. Loading embedding vector in string format require much more memory. ### Solution Modify the function `matchzoo.embedding.load_from_file` from: > data...
I want to rank a set of passages with a particular query and find the most similar one. How can i do that using matchzoo.
I'd like to ask if there are any communication groups that can communicate with each other.
### Describe the Question I was trying to implement the CDSSM model with the toy dataset provided and I get the following error.  Also the word hashing (preprocessing) is...
-------------------------------------------------------------------------------- CANT ENCODE -------------------------------------------------------------------------------- --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in 5 num_runs=10 6 ) ----> 7 results = tuner.tune() ~/anaconda3/envs/tensorflow/lib/python3.6/site-packages/matchzoo/auto/tuner/tuner.py in tune(self) 131 trials = hyperopt.Trials() 132 -->...
Hello! I recently watched the github/NTMC-Community/MatchZoo program and read the tutorial to understand it, but watching matchzoo is a bit embarrassing. I want to try using the toy dataset, run...