Giters

open-mmlab / mmdeploy

OpenMMLab Model Deployment Framework

Home Page:https://mmdeploy.readthedocs.io/en/latest/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

视频超分模型basicvsr-pp

Hongyuan-Liu opened this issue · comments

commented

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

我用的mmdeploy版本是1.3.1，部署视频超分模型basicvsr-pp，报下面的错误：
01/16 01:42:29 - mmengine - WARNING - Failed to search registry with scope "mmagic" in the "Codebases" registry tree. As a workaround, the current "Codebases" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmagic" is a correct scope, or whether the registry is initialized.
01/16 01:42:29 - mmengine - WARNING - Failed to search registry with scope "mmagic" in the "mmagic_tasks" registry tree. As a workaround, the current "mmagic_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmagic" is a correct scope, or whether the registry is initialized.
Traceback (most recent call last):
File "mmdeploy/tools/deploy.py", line 335, in
main()
File "mmdeploy/tools/deploy.py", line 129, in main
export2SDK(
File "/dataset/liuhongyuan/workspace/openmmlab/mmdeploy/mmdeploy/backend/sdk/export_info.py", line 353, in export2SDK
pipeline_info = get_pipeline(deploy_cfg, model_cfg, work_dir, device)
File "/dataset/liuhongyuan/workspace/openmmlab/mmdeploy/mmdeploy/backend/sdk/export_info.py", line 286, in get_pipeline
preprocess = get_preprocess(deploy_cfg, model_cfg, device=device)
File "/dataset/liuhongyuan/workspace/openmmlab/mmdeploy/mmdeploy/backend/sdk/export_info.py", line 207, in get_preprocess
assert transforms[0]['type'] == 'LoadImageFromFile',
AssertionError: The first item type of pipeline should be LoadImageFromFile

Reproduction

python mmdeploy/tools/deploy.py
mmdeploy/configs/mmagic/super-resolution/super-resolution_onnxruntime_static.py
mmagic/configs/basicvsr_pp/basicvsr-pp_c64n7_8xb1-600k_reds4.py
mmagic/checkpoint/basicvsr_plusplus_c64n7_8x1_600k_reds4_20210217-db622b2f.pth
mmpretrain/demo/demo.JPEG
--work-dir deploy_models/mmagic/basicvsr_plusplus_c64n7_8x1_600k_reds4
--device cpu
--dump-info

Environment

01/16 01:52:22 - mmengine - INFO - 

01/16 01:52:22 - mmengine - INFO - **********Environmental information**********
01/16 01:52:23 - mmengine - INFO - sys.platform: linux
01/16 01:52:23 - mmengine - INFO - Python: 3.8.16 (default, Jun 12 2023, 18:09:05) [GCC 11.2.0]
01/16 01:52:23 - mmengine - INFO - CUDA available: True
01/16 01:52:23 - mmengine - INFO - numpy_random_seed: 2147483648
01/16 01:52:23 - mmengine - INFO - GPU 0,1,2,3,4,5,6,7: NVIDIA GeForce RTX 3090
01/16 01:52:23 - mmengine - INFO - CUDA_HOME: /usr/local/cuda-11.8
01/16 01:52:23 - mmengine - INFO - NVCC: Cuda compilation tools, release 11.8, V11.8.89
01/16 01:52:23 - mmengine - INFO - GCC: gcc (Ubuntu 11.3.0-1ubuntu1~22.04.1) 11.3.0
01/16 01:52:23 - mmengine - INFO - PyTorch: 2.0.1+cu117
01/16 01:52:23 - mmengine - INFO - PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201703
  - Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.7
  - 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_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 8.9  (built against CUDA 11.8)
    - Built with CuDNN 8.5
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -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 -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.0.1, 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=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 

01/16 01:52:23 - mmengine - INFO - TorchVision: 0.15.2+cu117
01/16 01:52:23 - mmengine - INFO - OpenCV: 4.9.0
01/16 01:52:23 - mmengine - INFO - MMEngine: 0.10.2
01/16 01:52:23 - mmengine - INFO - MMCV: 2.1.0
01/16 01:52:23 - mmengine - INFO - MMCV Compiler: GCC 9.3
01/16 01:52:23 - mmengine - INFO - MMCV CUDA Compiler: 11.7
01/16 01:52:23 - mmengine - INFO - MMDeploy: 1.3.1+bc75c9d
01/16 01:52:23 - mmengine - INFO - 

01/16 01:52:23 - mmengine - INFO - **********Backend information**********
01/16 01:52:23 - mmengine - INFO - tensorrt:    None
01/16 01:52:23 - mmengine - INFO - ONNXRuntime: 1.8.1
01/16 01:52:23 - mmengine - INFO - ONNXRuntime-gpu:     None
01/16 01:52:23 - mmengine - INFO - ONNXRuntime custom ops:      Available
01/16 01:52:23 - mmengine - INFO - pplnn:       None
01/16 01:52:23 - mmengine - INFO - ncnn:        None
01/16 01:52:23 - mmengine - INFO - snpe:        None
01/16 01:52:23 - mmengine - INFO - openvino:    None
01/16 01:52:23 - mmengine - INFO - torchscript: 2.0.1
01/16 01:52:23 - mmengine - INFO - torchscript custom ops:      NotAvailable
01/16 01:52:23 - mmengine - INFO - rknn-toolkit:        None
01/16 01:52:23 - mmengine - INFO - rknn-toolkit2:       None
01/16 01:52:23 - mmengine - INFO - ascend:      None
01/16 01:52:23 - mmengine - INFO - coreml:      None
01/16 01:52:23 - mmengine - INFO - tvm: None
01/16 01:52:23 - mmengine - INFO - vacc:        None
01/16 01:52:23 - mmengine - INFO - 

01/16 01:52:23 - mmengine - INFO - **********Codebase information**********
01/16 01:52:24 - mmengine - INFO - mmdet:       3.3.0
01/16 01:52:24 - mmengine - INFO - mmseg:       None
01/16 01:52:24 - mmengine - INFO - mmpretrain:  1.2.0
01/16 01:52:24 - mmengine - INFO - mmocr:       None
01/16 01:52:24 - mmengine - INFO - mmagic:      1.2.0dev0
01/16 01:52:24 - mmengine - INFO - mmdet3d:     None
01/16 01:52:24 - mmengine - INFO - mmpose:      None
01/16 01:52:24 - mmengine - INFO - mmrotate:    None
01/16 01:52:24 - mmengine - INFO - mmaction:    None
01/16 01:52:24 - mmengine - INFO - mmrazor:     None
01/16 01:52:24 - mmengine - INFO - mmyolo:      None

Error traceback

No response