- Contrassegnare come Nuovo
- Preferito
- Iscriversi
- Disattiva notifiche
- Iscriversi a feed RSS
- Evidenziare
- Stampare
- Segnalare contenuto inappropriato
Hi,
In the documentation, human-pose-estimation models have their own specifications. May I know the meaning of this metric which is Average Precision (AP), GFlops, and MParams.
Thank you.
- Contrassegnare come Nuovo
- Preferito
- Iscriversi
- Disattiva notifiche
- Iscriversi a feed RSS
- Evidenziare
- Stampare
- Segnalare contenuto inappropriato
Hi Lc00,
Thank you for reaching out to us.
Average Precision (AP) is a key performance indicator and is defined by an area under the precision/recall curve. For further information you can refer to this article (This is an external link and is not maintained by Intel).
GFLOPs (Giga Floating Point Operations) are often used to describe how many operations that are required to run a single instance of a given model. This thread on Stack Overflow might help you to get a deeper insight.
MParams stands for Model Parameters. Parameters in general are weights that are learnt during training. They are weight matrices that contribute to model’s predictive power, changed during back-propagation process. For more information refer to this article (This is an external link and is not maintained by Intel).
Regards,
Hairul
Link copiato
- Contrassegnare come Nuovo
- Preferito
- Iscriversi
- Disattiva notifiche
- Iscriversi a feed RSS
- Evidenziare
- Stampare
- Segnalare contenuto inappropriato
Hi Lc00,
Thank you for reaching out to us.
Average Precision (AP) is a key performance indicator and is defined by an area under the precision/recall curve. For further information you can refer to this article (This is an external link and is not maintained by Intel).
GFLOPs (Giga Floating Point Operations) are often used to describe how many operations that are required to run a single instance of a given model. This thread on Stack Overflow might help you to get a deeper insight.
MParams stands for Model Parameters. Parameters in general are weights that are learnt during training. They are weight matrices that contribute to model’s predictive power, changed during back-propagation process. For more information refer to this article (This is an external link and is not maintained by Intel).
Regards,
Hairul
- Contrassegnare come Nuovo
- Preferito
- Iscriversi
- Disattiva notifiche
- Iscriversi a feed RSS
- Evidenziare
- Stampare
- Segnalare contenuto inappropriato
Hi Lc00,
This thread will no longer be monitored since this issue has been resolved. If you need any additional information from Intel, please submit a new question.
Regards,
Hairul

- Iscriversi a feed RSS
- Contrassegnare la discussione come nuova
- Contrassegnare la discussione come letta
- Sposta questo Discussione per l'utente corrente
- Preferito
- Iscriversi
- Pagina in versione di stampa