How can I use it to rank document after the model trainned?

sebastian-hofstaetter / matchmaker

Training & evaluation library for text-based neural re-ranking and dense retrieval models built with PyTorch

https://neural-ir-explorer.ec.tuwien.ac.at/

Apache License 2.0

261 stars 30 forks source link

How can I use it to rank document after the model trainned? #8

Closed cktsangal closed 3 years ago

cktsangal commented 4 years ago

I want know how can I feed the input data and get the ranking result from the trained model?

sebastian-hofstaetter commented 3 years ago

Hi, Sorry, for the super late reply - I forgot to monitor the repo. We have now updated the library and especially for dense retrieval we have many evaluation settings (via dense_retrieval.py). If you want to do re-ranking evaluation only you can use the --continue-folder setting of train.py Best, Sebastian