How can I fix the pytorch export model error? - pytorch

Question

1.by running the code below, you can reproduce the error
import torch
#torch.jit.script
def rotate_points_export(points):
return points
def xxx(input):
outputs = {}
outputs['a'] = input
outputs['b'] = input
outputs['b'] = rotate_points_export(outputs['b'])
return outputs
points = torch.rand((1,2,3,4))
model = torch.jit.trace(xxx, points, strict=False)
torch.jit.save(model, 'xx.pt')
The error messages are show below
model = torch.jit.trace(xxx, points, strict=False)
File "/home/intsig/codes/depedencies/hhdetection/lib/python3.8/site-packages/torch/jit/_trace.py", line 778, in trace
traced = torch._C._create_function_from_trace(
RuntimeError: values[i]->type()->isSubtypeOf(value_type) INTERNAL ASSERT FAILED at "/pytorch/torch/csrc/jit/ir/ir.cpp":1650, please report a bug to PyTorch.
The environ infos are show below
Collecting environment information...
PyTorch version: 1.7.1
Is debug build: False
CUDA used to build PyTorch: 10.2
ROCM used to build PyTorch: N/A
OS: Ubuntu 20.04.4 LTS (x86_64)
GCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0
Clang version: Could not collect
CMake version: version 3.16.3
Libc version: glibc-2.31
Python version: 3.8.10 (default, Mar 15 2022, 12:22:08) [GCC 9.4.0] (64-bit runtime)
Python platform: Linux-5.13.0-52-generic-x86_64-with-glibc2.29
Is CUDA available: True
CUDA runtime version: 11.1.74
GPU models and configuration: GPU 0: NVIDIA GeForce GTX 1080 Ti
Nvidia driver version: 470.129.06
cuDNN version: Probably one of the following:
/usr/local/cuda-11.1/targets/x86_64-linux/lib/libcudnn.so.8.0.5
/usr/local/cuda-11.1/targets/x86_64-linux/lib/libcudnn_adv_infer.so.8.0.5
/usr/local/cuda-11.1/targets/x86_64-linux/lib/libcudnn_adv_train.so.8.0.5
/usr/local/cuda-11.1/targets/x86_64-linux/lib/libcudnn_cnn_infer.so.8.0.5
/usr/local/cuda-11.1/targets/x86_64-linux/lib/libcudnn_cnn_train.so.8.0.5
/usr/local/cuda-11.1/targets/x86_64-linux/lib/libcudnn_ops_infer.so.8.0.5
/usr/local/cuda-11.1/targets/x86_64-linux/lib/libcudnn_ops_train.so.8.0.5
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
Versions of relevant libraries:
[pip3] numpy==1.21.1
[pip3] torch==1.7.1
[pip3] torchvision==0.8.2
[conda] blas 1.0 mkl
[conda] mkl 2021.2.0 h06a4308_296
[conda] mkl-service 2.3.0 py38h27cfd23_1
[conda] mkl_fft 1.3.0 py38h42c9631_2
[conda] mkl_random 1.2.1 py38ha9443f7_2
[conda] numpy 1.20.1 py38h93e21f0_0
[conda] numpy-base 1.20.1 py38h7d8b39e_0
[conda] numpydoc 1.1.0 pyhd3eb1b0_1