...
Note |
---|
If there is a node that is not a constant, it cannot be converted normally. In that case, convert the model using the following command, and perform quantization with the converted model. -m : before conversion model -o : after conversion model |
Code Block |
---|
$ graph_surgery.py onnx -m mobilenetv210.onnx -o mobilenetv210_mod.onnx -t Default |
Info |
---|
CAVALRY_VER is "2.1.7" for ambaCV2X, but please set "2.2.8.2" for ambaCV5X. |
Convert sample models
...
mobilenetv2
...