20,290
edits
Assembly Line Activity Recognition: Difference between revisions
m
→Inference performance
| Line 329: | Line 329: | ||
* GPU: NVIDIA Tesla T4 | * GPU: NVIDIA Tesla T4 | ||
The sample preprocessing could be accelerated since it is currently not running on the GPU; however by excluding this time, we can assure that the network is capable of performing inference at around 45 frames per second, but is currently limited at 0.91 frames per second due to inefficient preprocessing. The following table shows the results of the inference performance measurements over 50 samples. | The sample preprocessing could be accelerated since it is currently not running on the GPU; however, by excluding this time, we can assure that the network is capable of performing inference at around 45 frames per second, but is currently limited at 0.91 frames per second due to inefficient preprocessing. The following table shows the results of the inference performance measurements over 50 samples. | ||
<br> | |||
{| class="wikitable" style="margin-left: auto; margin-right: auto; border: none;" | {| class="wikitable" style="margin-left: auto; margin-right: auto; border: none;" | ||
|- | |- | ||