Xiaodong (Vincent) Huang
Xiaodong (Vincent) Huang
@Ricardosuzaku , seems like there is an implementation issue, could you share the onnx file? thanks
Thanks @Ricardosuzaku , confirmed this is TRT implementation issue and I have submit fix internally, and the fix will be available in the 8.0GA.
@Ricardosuzaku , when the onnx model contains Q/DQ, then you have to enable INT8 when import the ONNX, and there is no need to setup calibrator since the scale is...
Hello @Ricardosuzaku , with the line quant_modules.initialize() in the beginning of script, the created denseNet model in the later code will replaced conv/gemm with Q/DQ before it. Could you take...
@Ricardosuzaku , got it, Could you provide the verbose build log for the passed 7.2 and failed 8.0ea? thanks! TRT_LOGGER = trt.Logger(trt.Logger.VERBOSE)
@Ricardosuzaku , could you redirect to a file like: python builder.py > build.log Thanks
Hi @Ricardosuzaku , thanks for the log but I did not see regression between `TRT7.2_opset9_int8_True_calib.log` and `TRT8.0_opset13_int8_True_calib.log` Both engine has trt accuracy {'top1_prec': 0.01, 'top5_prec': 0.05} I thought you have...
@Ricardosuzaku , the code is correct, the new API behavior the same internally, do you have the 7.2 log that use `builder.int8_mode=True`?
sorry @Ricardosuzaku , I still not cannot see the log
@PowerDi we did not see any functional bug for YOLOv5 INT8. Could you elaborate more? Thanks