Poor INT8 Results for New TensorRT4.0.1.6 ?

I try to upgrade the tensorrt version from tensorrt3.0.4 to tensorrt4.0.6, but I find ssd detection results with int8 precision are too poor! Nothing is changed except for the *.so libs and include headers.

When I just upgrade tensorrt version from tensorrt3.04 to tensorrt4.0.0.3(RC), the results is same with tensorrt3.

I also find the calibration tables for TRT3 and TRT4 are different, 1X1 convolution layers are not included in tensorrt4.

So, is there any changes for int8 calibration/implementation in the new released TRT4.0.6??

Three int8 detection results for 3 distinct tensorrt version are here:

hi, I got the same problem just like yours.
Did you fix it ? Does anyone can answer this question?