Table 9 ResNet34 model information for embedded devices.

From: Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML

MSE (mg/dL)2

795.3

MAE (mg/dL)

18.8

Inference time on embedded device (sec)

6.4

Model size before modifications

22 MB

Model size after modifications

7 MB

Params Count

7 million

Back to article page