yolox-nano 在k210量化损失

[LYHTZHANGJIANG]

Describe the bug
A clear and concise description of what the bug is.

To Reproduce
Command line or scripts to reproduce the behavior:

Expected behavior
A clear and concise description of what you expected to happen.

Origin model and code
If applicable, add orgin model and code to help explain your problem.

Environment (please complete the following information):

• OS: [e.g. Ubuntu18.04]
• nncase version [e.g. v1.0.0.dev24]
• DL Framework [e.g. TensorFlow 2.5.0]

Additional context
Add any other context about the problem here.

[LYHTZHANGJIANG]

nncase1.6.0，就跑的官方的20个类别的demo。
1、编译cpu的定点模型，输出是正常。
2、但是编译210的定点模型
python tools/compile.py model/yolox_nano_224.onnx yolox_nano_224_quant.kmodel --imgs_dir ../20classes_yolo/images/ --legacy --target k210
python tools/simulate.py yolox_nano_224_quant.kmodel ../20classes_yolo/images/dog.bmp
这张dog.bmp的图片只能输出一个车，并且还没框准确。