An Improved EfficientNetV2 Model Based on Visual Attention Mechanism: Application to Identification of Cassava Disease

Table 2

The time comparison table of adding random depth and not adding random depth. The training time is the time it takes for the model to train for 120 epochs. The meaning of inference time is the time it takes for the model to predict a single image.

Model	Train time (h)	Infer time (s)
With dropout	35	1.01
No dropout	49	1.4