Table 8.
Training and inference time of the models on Tesla P100 GPU.
| Model name | Training time per epoch | Inference time per image |
|---|---|---|
| Xception | 356 s | 65.4 ms |
| ResNet50V2 | 195 s | 52.6 ms |
| Our Model | 198 s | 66.1 ms |
Official websites use .gov
A
.gov website belongs to an official
government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you've safely
connected to the .gov website. Share sensitive
information only on official, secure websites.