search

open-mmlab / mmdeploy

OpenMMLab Model Deployment Framework
https://mmdeploy.readthedocs.io/en/latest/
Apache License 2.0
2.78k stars 637 forks source link

[bug] run deploy.py have no .json and .pipeline #1557

Closed Viki-researcher closed 1 year ago

Viki-researcher commented 1 year ago

Checklist

Describe the bug

Run deploy.py have no deploy.json, detail.json, pipeline.json. only end2end.engine and end2end.onnx.

Reproduction

run E:\Mmdet\mmdeploy-0.5.0\tools\deploy.py

Environment

2022-12-20 15:18:29,317 - mmdeploy - INFO - **********Environmental information**********
fatal: not a git repository (or any of the parent directories): .git
2022-12-20 15:18:53,191 - mmdeploy - INFO - sys.platform: win32
2022-12-20 15:18:53,191 - mmdeploy - INFO - Python: 3.8.8 (default, Apr 13 2021, 15:08:03) [MSC v.1916 64 bit (AMD64)]
2022-12-20 15:18:53,191 - mmdeploy - INFO - CUDA available: True
2022-12-20 15:18:53,191 - mmdeploy - INFO - GPU 0: NVIDIA GeForce GTX 1660 Ti
2022-12-20 15:18:53,191 - mmdeploy - INFO - CUDA_HOME: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.4       
2022-12-20 15:18:53,191 - mmdeploy - INFO - NVCC: Cuda compilation tools, release 11.4, V11.4.48
2022-12-20 15:18:53,191 - mmdeploy - INFO - MSVC: 用于 x64 的 Microsoft (R) C/C++ 优化编译器 19.29.30137 版
2022-12-20 15:18:53,192 - mmdeploy - INFO - GCC: n/a
2022-12-20 15:18:53,192 - mmdeploy - INFO - PyTorch: 1.11.0+cu113
2022-12-20 15:18:53,192 - mmdeploy - 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 v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e)
  - OpenMP 2019
  - LAPACK is enabled (usually provided by MKL)
  - 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 2.5.4
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, 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=1.11.0, 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=OFF, USE_NNPACK=OFF, USE_OPENMP=ON, USE_ROCM=OFF,

2022-12-20 15:18:53,195 - mmdeploy - INFO - TorchVision: 0.12.0+cu113
2022-12-20 15:18:53,196 - mmdeploy - INFO - OpenCV: 4.5.2
2022-12-20 15:18:53,196 - mmdeploy - INFO - MMCV: 1.5.2
2022-12-20 15:18:53,196 - mmdeploy - INFO - MMCV Compiler: MSVC 192930140
2022-12-20 15:18:53,196 - mmdeploy - INFO - MMCV CUDA Compiler: 11.3
2022-12-20 15:18:53,197 - mmdeploy - INFO - MMDeploy: 0.5.0+
2022-12-20 15:18:53,197 - mmdeploy - INFO -

2022-12-20 15:18:53,197 - mmdeploy - INFO - **********Backend information**********
2022-12-20 15:18:57,257 - mmdeploy - INFO - onnxruntime: 1.12.0 ops_is_avaliable : True
2022-12-20 15:18:57,327 - mmdeploy - INFO - tensorrt: 8.2.3.0   ops_is_avaliable : True
2022-12-20 15:18:57,384 - mmdeploy - INFO - ncnn: None  ops_is_avaliable : False
2022-12-20 15:18:57,393 - mmdeploy - INFO - pplnn_is_avaliable: False
2022-12-20 15:18:57,404 - mmdeploy - INFO - openvino_is_avaliable: False
2022-12-20 15:18:57,405 - mmdeploy - INFO -

2022-12-20 15:18:57,405 - mmdeploy - INFO - **********Codebase information**********
2022-12-20 15:18:57,417 - mmdeploy - INFO - mmdet:      2.25.0
2022-12-20 15:18:57,417 - mmdeploy - INFO - mmseg:      None
2022-12-20 15:18:57,417 - mmdeploy - INFO - mmcls:      None
2022-12-20 15:18:57,418 - mmdeploy - INFO - mmocr:      None
2022-12-20 15:18:57,418 - mmdeploy - INFO - mmedit:     None
2022-12-20 15:18:57,419 - mmdeploy - INFO - mmdet3d:    None
2022-12-20 15:18:57,419 - mmdeploy - INFO - mmpose:     None
2022-12-20 15:18:57,420 - mmdeploy - INFO - mmrotate:   None

Error traceback

def parse_args():
    parser = argparse.ArgumentParser(description='Export model to backends.')
    parser.add_argument('--deploy_cfg',default=r'E:\Mmdet\mmdeploy-0.11.0\configs\mmdet\detection\detection_tensorrt-fp16_static-800x1344.py', help='deploy config path')
    parser.add_argument('--model_cfg', default=r'E:\Mmdet\mmdetection_2.25\mmdetection\configs\faster_rcnn\faster_rcnn_r50_fpn_mstrain_3x_coco.py',help='model config path')
    parser.add_argument('--checkpoint', default=r'E:\MmDet\m2v1.0_portable_convert\models/faster_rcnn_r50_fpn_mstrain_3x_coco_20210524_110822-e10bd31c.pth',help='model checkpoint path')
    parser.add_argument('--img', default=r'E:\Mmdet\mmdeploy-0.11.0\demo\resources/det.jpg',help='image used to convert model model')
    parser.add_argument(
        '--test-img', default=r'E:\Mmdet\mmdeploy-0.11.0\demo\resources/det.jpg', help='image used to test model')
    parser.add_argument(
        '--work-dir',
        default=r'E:\Mmdet\mmdeploy-0.4.0\work_dir',
        help='the dir to save logs and models')
    parser.add_argument(
        '--calib-dataset-cfg',
        help='dataset config path used to calibrate in int8 mode. If not \
            specified,it will use "val" dataset in model config instead.',
        default=None)
    parser.add_argument(
        '--device', help='device used for conversion', default='cuda:0')
lvhan028 commented 1 year ago

use --dump-info in the command

Viki-researcher commented 1 year ago

use --dump-info in the command

thanks,it solve