[Bug] Do not generate * .json file

[manhta26]

Checklist

• I have searched related issues but cannot get the expected help.
• 2. I have read the FAQ documentation but cannot get the expected help.
• 3. The bug has not been fixed in the latest version.

Describe the bug

When convert model to onnx do not generate *json file.
Only onnx and output image file saved.
Version :
mmdeploy 1.3.1
Onnxruntime 1.19.1

Reproduction

python tools/deploy.py configs/mmpretrain/classification_onnxruntime_dynamic.py configs/efficientnet_v2/efficientnetv2-b3.py best_epoch_100.pth --device cuda

Environment

[Tạ Đức Mạnh] 03-14-2025 17:11
[Tạ Đức Mạnh] 03-14-2025 17:06
03/14 17:04:50 - mmengine - INFO - **********Environmental information**********
03/14 17:05:21 - mmengine - INFO - sys.platform: win32
03/14 17:05:21 - mmengine - INFO - Python: 3.9.0b5 (tags/v3.9.0b5:8ad7d50, Jul 20 2020, 18:35:09) [MSC v.1924 64 bit (AMD64)]
03/14 17:05:21 - mmengine - INFO - CUDA available: True
03/14 17:05:21 - mmengine - INFO - MUSA available: False
03/14 17:05:21 - mmengine - INFO - numpy_random_seed: 2147483648
03/14 17:05:21 - mmengine - INFO - GPU 0: NVIDIA GeForce RTX 4070 Laptop GPU
03/14 17:05:21 - mmengine - INFO - CUDA_HOME: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7
03/14 17:05:21 - mmengine - INFO - NVCC: Cuda compilation tools, release 11.7, V11.7.64
03/14 17:05:21 - mmengine - INFO - MSVC: Microsoft (R) C/C++ Optimizing Compiler Version 19.41.34120 for x64
03/14 17:05:21 - mmengine - INFO - GCC: n/a
03/14 17:05:21 - mmengine - INFO - PyTorch: 1.13.0+cu117
03/14 17:05:21 - mmengine - INFO - PyTorch compiling details: PyTorch built with:
  - C++ Version: 199711
  - MSVC 192829337
  - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
  - OpenMP 2019
  - LAPACK is enabled (usually provided by MKL)
  - CPU capability usage: AVX2
  - CUDA Runtime 11.7
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
  - CuDNN 8.5
  - Magma 2.5.4
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=C:/actions-runner/_work/pytorch/pytorch/builder/windows/tmp_bin/sccache-cl.exe, CXX_FLAGS=/DWIN32 /D_WINDOWS /GR /EHsc /w /bigobj -DUSE_PTHREADPOOL -openmp:experimental -IC:/actions-runner/_work/pytorch/pytorch/builder/windows/mkl/include -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOCUPTI -DUSE_FBGEMM -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=OFF, USE_OPENMP=ON, USE_ROCM=OFF,

03/14 17:05:21 - mmengine - INFO - TorchVision: 0.14.0+cu117
03/14 17:05:21 - mmengine - INFO - OpenCV: 4.11.0
03/14 17:05:21 - mmengine - INFO - MMEngine: 0.10.7
03/14 17:05:21 - mmengine - INFO - MMCV: 2.1.0
03/14 17:05:21 - mmengine - INFO - MMCV Compiler: MSVC 192930148
03/14 17:05:21 - mmengine - INFO - MMCV CUDA Compiler: 11.7
03/14 17:05:21 - mmengine - INFO - MMDeploy: 1.3.1+
03/14 17:05:21 - mmengine - INFO -03/14 17:05:21 - mmengine - INFO - **********Backend information**********
03/14 17:05:22 - mmengine - INFO - tensorrt:    None
03/14 17:05:22 - mmengine - INFO - ONNXRuntime: 1.19.2
03/14 17:05:22 - mmengine - INFO - ONNXRuntime-gpu:     1.15.1
03/14 17:05:22 - mmengine - INFO - ONNXRuntime custom ops:      Available

Error traceback