Akida x86 Evaluation Kit -
User Guide
P a g e
|
6
5.3
A
KIDA
C
LASSIFICATION DEMO
This application uses the MobileNet/ImageNet model from akida-models to classify Webcam
frames. This demo requires a USB camera.
Enter
python classification_demo.py
Place objects in front of the camera for prediction.
Figure 4
: Classification demonstration window
5.4
A
KIDA EDGE LEARNING DEMO
This application uses MobileNet models replacing the last layer to learn new classes from the
Webcam frames. This demo requires a USB camera.
Enter
python edge_demo.py
Enter class name in the label field and click
Learn new class
for each new class. Start with
background as the first class. Next choose other objects the same or similar to images in the
ImageNet dataset for best results. For testing, place learned object in the field of view.
