No converter registered for op type: Identity

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

I try convert onnx into tensorrt plan file for restnet-50, but report error:

.input: "convolution_output48"
output: "activation_output48"
name: "Identity48"
op_type: "Identity"
domain: ""
terminate called after throwing an instance of 'std::out_of_range'
  what():  No converter registered for op type: Identity
Aborted (core dumped)

any good suggestions to avoid it?

2

Hello, can you provide details on the platforms you are using?

Linux distro and version
GPU type 
nvidia driver version
CUDA version
CUDNN version
Python version [if using python]
Tensorflow version 
TensorRT version

Any usage/source file you can provide will help us debug too.

3

i have the same type error
CUDA:9.0
OS:centos
torch:1.1.0
tensorrt:4.0.1.6
model:pix2pixhd
cudnn:9.0
gpu:Tesla V100

wen i run onnx on trt:
python test.py --name label2city_1024p --netG global --label_nc 0 --no_instance --onnx ./test.onnx
error:
input: “207”
input: “208”
input: “209”
output: “210”
op_type: “InstanceNormalization”
attribute {
name: “epsilon”
f: 1e-05
type: FLOAT
}
terminate called after throwing an instance of ‘std::out_of_range’
what(): No converter registered for op type: InstanceNormalization
Aborted