About the answer prediction
Abierto
- Lenguaje dominante
- Python
- Estrellas
- 435
- Forks
- 118
- Métricas de merge de PR
- Sin PR fusionados en 30 d
Descripción
Hi Christopher,
I still have a small question:
In Class BoundaryPrediction at docqa/nn/span_prediction.py, in function get_best_span(), I find you convert start_logits and end_logits to function best_span_from_bounds().
As far as I am concerned, we should convert tf.nn.log_softmax(start_logits) && tf.nn.log_softmax(end_logits) rather than start_logits&end_logits ?
Thanks a lot for your time!
YeDeming
Guía de contribución
No hay ninguna guía de contribución indexada para este repositorio
Evaluación
Este issue todavía no se ha evaluado.