tf -> onnx -> trt, it’s ok when I use tensorrt_18.104.22.168 with FP32 mode, but something wrong with int8 calibration:
[TensorRT] INTERNAL ERROR: Assertion failed: d.nbDims >= 1
To solve the problem, I try the tensorrt_7.1.3 with FP32, the same code/onnx file : ./trtexec --onnx=./test.onnx, however:
[TRT] Repeated layer name: stage2/split_1 (layers must have distinct names)
I check the onnx, but all split_xx node with different names, not repeated, and tensorrt_22.214.171.124 with FP32 mode is ok, no error!
the test.onnx is converted by tf2onnx, I test the other onnx file (from pytorch), TensorRT-126.96.36.199 runs successfully.
Finally, I replace the TensorRT-188.8.131.52/lib/libnvonnxparser.so.7.1.xxx with TensorRT-184.108.40.206/lib/libnvonnxparser.so.7.0.xxx, everything works —FP32/16 and int8 calib.
this is confusing!
TensorRT Version: 7.1.3
GPU Type: T4
Nvidia Driver Version: 440.82
CUDA Version: 10.2
CUDNN Version: 8.0
Operating System + Version: centos7
Python Version (if applicable): 3.6.4
TensorFlow Version (if applicable): 1.14