'DataContainer' object is not subscriptable during TensorRT

[Auth0rM0rgan]

Hello,

Im trying to convert CRNN text recognition model to TensorRT backbone but getting an error. I was able to convert the pytorch model to TensorRT without any issue and also i was able to measure the performance without error. However, when I try to evaluate the model Im facing the following error. Any idea how can I solve the issue??

2022-01-25 11:29:44,658 - mmdeploy - INFO - Sorting the dataset by 'height' and 'width' is not possible.
2022-01-25 11:29:44,783 - mmdeploy - INFO - Successfully loaded tensorrt plugins from /home/Documents/Dev/MMDeploy/build/lib/libmmdeploy_tensorrt_ops.so
2022-01-25 11:29:44,783 - mmdeploy - INFO - Successfully loaded tensorrt plugins from /home/Documents/Dev/MMDeploy/build/lib/libmmdeploy_tensorrt_ops.so
[01/25/2022-11:29:45] [TRT] [W] TensorRT was linked against cuBLAS/cuBLAS LT 11.6.3 but loaded cuBLAS/cuBLAS LT 11.5.1
[01/25/2022-11:29:46] [TRT] [W] TensorRT was linked against cuBLAS/cuBLAS LT 11.6.3 but loaded cuBLAS/cuBLAS LT 11.5.1
[                                                  ] 0/7672, elapsed: 0s, ETA:Traceback (most recent call last):
  File "./tools/test.py", line 140, in <module>
    main()
  File "./tools/test.py", line 133, in main
    args.show_dir)
  File "/home/Documents/Dev/MMDeploy/mmdeploy/codebase/base/task.py", line 138, in single_gpu_test
    out_dir, **kwargs)
  File "/home/Documents/Dev/MMDeploy/mmdeploy/codebase/mmocr/deploy/mmocr.py", line 141, in single_gpu_test
    outputs = single_gpu_test(model, data_loader, show, out_dir, **kwargs)
  File "/home/anaconda3/envs/mmdeploy/lib/python3.7/site-packages/mmdet/apis/test.py", line 32, in single_gpu_test
    if batch_size == 1 and isinstance(data['img'][0], torch.Tensor):
TypeError: 'DataContainer' object is not subscriptable

This is the command I use to evaluate the performance

DEPLOY_CFG="configs/mmocr/text-recognition/text-recognition_tensorrt-fp16_dynamic-1x32x32-1x32x640.py"
MODEL_CFG="/home/Documents/Dev/mmocr/configs/textrecog/crnn/crnn_academic_dataset.py"

python ./tools/test.py ${DEPLOY_CFG} ${MODEL_CFG} --model "/home/Desktop/ocr-tensorRT/end2end.engine" --out /home/Desktop/ocr-tensorRT/out/out_ocr.pkl --show-dir "/home/Desktop/ocr-tensorRT"

Thanks!

[RunningLeon]

@Auth0rM0rgan Hi, could you post the version of mmocr and mmdet here?

[Auth0rM0rgan]

@RunningLeon, The command I mentioned works without show-dir however when I specify the --show or --show-dir I get the error I meantioned.

mmocr = '0.4.0'
mmcv = '1.4.4'
mmdeploy = '0.1.0'

[RunningLeon]

@RunningLeon, The command I mentioned works without show-dir however when I specify the --show or --show-dir I get the error I meantioned.

mmocr = '0.4.0'
mmcv = '1.4.4'
mmdeploy = '0.1.0'

@Auth0rM0rgan Hi, please try with mmocr=0.3.0 as to here:

mmdeploy/requirements/optional.txt

Line 4 in 57a9d9b

mmocr==0.3.0

[Auth0rM0rgan]

@RunningLeon, You mean I should remove my current mmocr which is version "0.4.0" and compile the version "0.3.0"?

[RunningLeon]

@RunningLeon, You mean I should remove my current mmocr which is version "0.4.0" and compile the version "0.3.0"?
@Auth0rM0rgan
Hi, could install by pip install mmocr==0.3.0.

[Auth0rM0rgan]

pip install mmocr==0.3.0

@RunningLeon, No success, Im still getting the same error even with installing mmocr=0.3.0. I also downgrade MMCV to 1.4.0 since mmocr 0.3.0 is not compatible with MMCV 1.4.4. I installed all the basecodes from source.

[RunningLeon]

pip install mmocr==0.3.0

@RunningLeon, No success, Im still getting the same error even with installing mmocr=0.3.0. I also downgrade MMCV to 1.4.0 since mmocr 0.3.0 is not compatible with MMCV 1.4.4. I installed all the basecodes from source.

@Auth0rM0rgan Thanks for your feedback, we'll look into it.

[Auth0rM0rgan]

@RunningLeon, Thanks, hope it solve soon. Here is my environment in case you need to reproduce the error.

2022-01-26 09:50:31,796 - mmdeploy - INFO - sys.platform: linux
2022-01-26 09:50:31,796 - mmdeploy - INFO - Python: 3.7.12 | packaged by conda-forge | (default, Oct 26 2021, 06:08:21) [GCC 9.4.0]
2022-01-26 09:50:31,796 - mmdeploy - INFO - CUDA available: True
2022-01-26 09:50:31,796 - mmdeploy - INFO - GPU 0: NVIDIA GeForce RTX 3080
2022-01-26 09:50:31,796 - mmdeploy - INFO - CUDA_HOME: /usr/local/cuda
2022-01-26 09:50:31,796 - mmdeploy - INFO - NVCC: Build cuda_11.4.r11.4/compiler.30033411_0
2022-01-26 09:50:31,796 - mmdeploy - INFO - GCC: gcc (Ubuntu 9.3.0-17ubuntu1~20.04) 9.3.0
2022-01-26 09:50:31,796 - mmdeploy - INFO - PyTorch: 1.10.1
2022-01-26 09:50:31,796 - mmdeploy - INFO - PyTorch compiling details: PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740)
  - 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_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 8.2
  - 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-variable -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=1.10.1, 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=ON, USE_NNPACK=ON, USE_OPENMP=ON, 

2022-01-26 09:50:31,796 - mmdeploy - INFO - TorchVision: 0.11.2
2022-01-26 09:50:31,796 - mmdeploy - INFO - OpenCV: 4.5.5
2022-01-26 09:50:31,796 - mmdeploy - INFO - MMCV: 1.4.0
2022-01-26 09:50:31,796 - mmdeploy - INFO - MMCV Compiler: GCC 9.3
2022-01-26 09:50:31,796 - mmdeploy - INFO - MMCV CUDA Compiler: 11.4
2022-01-26 09:50:31,796 - mmdeploy - INFO - MMDeployment: 0.1.0+c74c41b
2022-01-26 09:50:31,941 - mmdeploy - INFO - onnxruntime: None ops_is_avaliable : False
2022-01-26 09:50:31,941 - mmdeploy - INFO - tensorrt: 8.2.1.8 ops_is_avaliable : True
2022-01-26 09:50:31,941 - mmdeploy - INFO - ncnn: None ops_is_avaliable : False
2022-01-26 09:50:31,941 - mmdeploy - INFO - pplnn_is_avaliable: False
2022-01-26 09:50:31,942 - mmdeploy - INFO - openvino_is_avaliable: False

[RunningLeon]

@Auth0rM0rgan Hi, this is a bug of upstream repo mmocr, and will be fixed later by maintainers of mmocr.

[Harold-lkk]

@RunningLeon, The command I mentioned works without show-dir however when I specify the --show or --show-dir I get the error I meantioned.

mmocr = '0.4.0'
mmcv = '1.4.4'
mmdeploy = '0.1.0'

MMOCR has fixed this issue in mmocr = '0.4.1', more detail can be found in https://github.com/open-mmlab/mmocr/releases/tag/v0.4.1. You can install the latest mmocr.

[RunningLeon]

Feel free to reopen if still have same issue.