[Bug] It does not support 32bit tiff

[Liiiifeie]

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

I used mmdeploy to convert my mmseg model to onnx. It works properly on 8bit png/tiff, but it does work on 32 bit tiff. This problem does not occur during training and testing stage.

Reproduction

mmdeploy/tools/deploy.py
mmdeploy/configs/mmseg/segmentation_onnxruntime_dynamic.py
configs/Mymmseg/512x512_potsdam.py
pth/best_mIoU_iter_34500.pth
32img/top_dsm_test.tif
--work-dir onnx

Environment

2024-10-22 09:09:24,807 - mmdeploy - INFO - **********Environmental information**********
2024-10-22 09:09:25,160 - mmdeploy - INFO - sys.platform: linux
2024-10-22 09:09:25,160 - mmdeploy - INFO - Python: 3.8.8 (default, Apr 13 2021, 19:58:26) [GCC 7.3.0]
2024-10-22 09:09:25,160 - mmdeploy - INFO - CUDA available: True
2024-10-22 09:09:25,160 - mmdeploy - INFO - GPU 0: Tesla P100-PCIE-16GB
2024-10-22 09:09:25,160 - mmdeploy - INFO - CUDA_HOME: /usr/local/cuda
2024-10-22 09:09:25,160 - mmdeploy - INFO - NVCC: Cuda compilation tools, release 11.3, V11.3.58
2024-10-22 09:09:25,160 - mmdeploy - INFO - GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
2024-10-22 09:09:25,160 - mmdeploy - INFO - PyTorch: 1.11.0+cu113
2024-10-22 09:09:25,160 - mmdeploy - INFO - PyTorch compiling details: PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) oneAPI Math Kernel Library Version 2021.2-Product Build 20210312 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.3
  - 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_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
  - CuDNN 8.2
  - Magma 2.5.2
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.11.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 

2024-10-22 09:09:25,160 - mmdeploy - INFO - TorchVision: 0.12.0+cu113
2024-10-22 09:09:25,160 - mmdeploy - INFO - OpenCV: 4.10.0
2024-10-22 09:09:25,160 - mmdeploy - INFO - MMCV: 1.7.1
2024-10-22 09:09:25,160 - mmdeploy - INFO - MMCV Compiler: GCC 9.3
2024-10-22 09:09:25,160 - mmdeploy - INFO - MMCV CUDA Compiler: 11.3
2024-10-22 09:09:25,160 - mmdeploy - INFO - MMDeploy: 0.14.0+e09134d
2024-10-22 09:09:25,160 - mmdeploy - INFO - 

2024-10-22 09:09:25,160 - mmdeploy - INFO - **********Backend information**********
2024-10-22 09:09:25,176 - mmdeploy - INFO - tensorrt:	None
/root/miniconda3/lib/python3.8/site-packages/pkg_resources/__init__.py:116: PkgResourcesDeprecationWarning: 4.0.0-unsupported is an invalid version and will not be supported in a future release
  warnings.warn(
2024-10-22 09:09:25,259 - mmdeploy - INFO - ONNXRuntime:	1.8.1
2024-10-22 09:09:25,259 - mmdeploy - INFO - ONNXRuntime-gpu:	None
2024-10-22 09:09:25,259 - mmdeploy - INFO - ONNXRuntime custom ops:	Available
2024-10-22 09:09:25,260 - mmdeploy - INFO - pplnn:	None
2024-10-22 09:09:25,262 - mmdeploy - INFO - ncnn:	None
2024-10-22 09:09:25,263 - mmdeploy - INFO - snpe:	None
2024-10-22 09:09:25,264 - mmdeploy - INFO - openvino:	None
2024-10-22 09:09:25,266 - mmdeploy - INFO - torchscript:	1.11.0+cu113
2024-10-22 09:09:25,266 - mmdeploy - INFO - torchscript custom ops:	NotAvailable
2024-10-22 09:09:25,392 - mmdeploy - INFO - rknn-toolkit:	None
2024-10-22 09:09:25,392 - mmdeploy - INFO - rknn2-toolkit:	None
2024-10-22 09:09:25,393 - mmdeploy - INFO - ascend:	None
2024-10-22 09:09:25,394 - mmdeploy - INFO - coreml:	None
2024-10-22 09:09:25,395 - mmdeploy - INFO - tvm:	None
2024-10-22 09:09:25,395 - mmdeploy - INFO - 

2024-10-22 09:09:25,395 - mmdeploy - INFO - **********Codebase information**********
2024-10-22 09:09:25,397 - mmdeploy - INFO - mmdet:	None
2024-10-22 09:09:25,397 - mmdeploy - INFO - mmseg:	0.30.0
2024-10-22 09:09:25,398 - mmdeploy - INFO - mmcls:	0.25.0
2024-10-22 09:09:25,398 - mmdeploy - INFO - mmocr:	None
2024-10-22 09:09:25,398 - mmdeploy - INFO - mmedit:	None
2024-10-22 09:09:25,398 - mmdeploy - INFO - mmdet3d:	None
2024-10-22 09:09:25,398 - mmdeploy - INFO - mmpose:	None
2024-10-22 09:09:25,398 - mmdeploy - INFO - mmrotate:	None
2024-10-22 09:09:25,398 - mmdeploy - INFO - mmaction:	None

Error traceback

[ WARN:[email protected]] global grfmt_tiff.cpp:710 readData OpenCV TIFF: TIFFRGBAImageOK: Sorry, can not handle images with 32-bit samples
Process Process-2:
Traceback (most recent call last):
  File "/root/miniconda3/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap
    self.run()
  File "/root/miniconda3/lib/python3.8/multiprocessing/process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/mmdeploy/apis/core/pipeline_manager.py", line 107, in __call__
    ret = func(*args, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/mmdeploy/apis/pytorch2onnx.py", line 65, in torch2onnx
    data, model_inputs = task_processor.create_input(img, input_shape)
  File "/root/miniconda3/lib/python3.8/site-packages/mmdeploy/codebase/mmseg/deploy/segmentation.py", line 145, in create_input
    data = test_pipeline(data)
  File "/root/miniconda3/lib/python3.8/site-packages/mmseg/datasets/pipelines/compose.py", line 41, in __call__
    data = t(data)
  File "/root/miniconda3/lib/python3.8/site-packages/mmseg/datasets/pipelines/loading.py", line 60, in __call__
    filename = results['img_info']['filename']
KeyError: 'img_info'
2024-10-22 09:12:13,116 - mmdeploy - ERROR - `mmdeploy.apis.pytorch2onnx.torch2onnx` with Call id: 0 failed. exit.