【量化测试】

文章目录


在这里插入图片描述

量化前
在这里插入图片描述
量化后
在这里插入图片描述

#Dynamic quantization  动态量化
import onnx
from onnxruntime.quantization import quantize_dynamic, QuantType
 
model_fp32 = 'path/to/the/model.onnx'
model_quant = 'path/to/the/model.quant.onnx'
quantized_model = quantize_dynamic(model_fp32, model_quant, weight_type=QuantType.QUInt8)
--------------------------
# QAT quantization  QAT量化
import onnx
from onnxruntime.quantization import quantize_qat, QuantType
 
model_fp32 = 'path/to/the/model.onnx'
model_quant = 'path/to/the/model.quant.onnx'
quantized_model = quantize_qat(model_fp32, model_quant)

猜你喜欢

转载自blog.csdn.net/weixin_42483745/article/details/125950071