MatchZoo-py

MatchZoo-py copied to clipboard

For drmm model, dense_output should be flipped at dim=-1?

3

Hi, In drmm model, Should it be **x = torch.einsum('bl,bl->b', torch.flip(dense_output,(-1,)), attention_probs)** Instead of x = torch.einsum('bl,bl->b', dense_output, attention_probs) After I revise this, I got the training loss reduction much...

wangcongcong123

Add on-the-fly sampling

2

As far as I understand, right now text pairs are picked directly using Datapack samples. However it is almost impossible to mine "hard" negative samples before training. Just adding into...

lebionick

Dataset Builder creates duplicate query-document pairs & model predictions are odd

1

I have the following issue, which is really odd and affects the evaluation of the neural models. I build my data using the auto preparer and I came to realize,...

littlewine

Use of trainer/runer and number of training epochs

1

Hi, I have a question regarding choosing the epochs and doing hyperparameter tuning in general. I am currently using `matchzoo.trainers.trainer` to train my models with the default number of epochs(=10)....

littlewine

bert processor

4

When i use bert processor to tranform my dataset, there will appear a warning: Token indices sequence length is longer than the specified maximum sequence length for this model (694...

xuezzz

### Describe the Question Please provide a clear and concise description of what the question is. I am on matchzoo-py1.1.1 and when I try to play with the codemz.auto.Tuner ,...

ZhqZhqZhq

How to get the actual rank using trainer.predict()?

3

### Describe the Question I am trying to get the rank out of a trained model (using trainer). However, when I do `trainer.predict()` I get back a numpy array of...

littlewine

Error during training because of float length of sequence(?)

1

### Describe the bug Hi, I have the following issue: when I am trying to train my model using `trainer.run()`, I get the following error: ``` Traceback (most recent call...

littlewine

I have a task in which I need to match several texts with huge (~1M texts) database. Even though available models are pretty fast, this is not enough. The best...

lebionick

Feature/add metrics

1

caiyinqiong