tuochi

The time of model inference increases after doing int8 quantization

5

my device is i7-8750H Start Benchmark with openvino (Batchsize = 1) Time span (FP32 MODE): 68.0568 sec Time span (INT8 MODE): 85.6443 sec i don't konw what is happend, how...

i want to using python to connect your lidar device but i can not success. device is mid-360