How do I generate INT8 calibration file wiht caffe?

Description

I want to quantize a caffe model with TensorRT, in order to NVDLA.
But I can’t find tutorials about it.
How do I generate INT8 calibration file with cpp or Python API?

NVDLA Low Precision:

Hi @Supine
Please refer to the below link


https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#dla_topic

Thanks!