YOLOv5 in DOTA with CSL_label.(Oriented Object Detection)(Rotation Detection)(Rotated BBox)

Overview

YOLOv5_DOTA_OBB

YOLOv5 in DOTA_OBB dataset with CSL_label.(Oriented Object Detection)

Datasets and pretrained checkpoint

Fuction

  • train.py. Train.

  • detect.py. Detect and visualize the detection result. Get the detection result txt.

  • evaluation.py. Merge the detection result and visualize it. Finally evaluate the detector

Installation (Linux Recommend, Windows not Recommend)

1. Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$   pip install -r requirements.txt

2. Install swig

$   cd  \.....\yolov5_DOTA_OBB\utils
$   sudo apt-get install swig

3. Create the c++ extension for python

$   swig -c++ -python polyiou.i
$   python setup.py build_ext --inplace

More detailed explanation

想要了解相关实现的细节和原理可以看我的知乎文章:
YOLOv5_DOTAv1.5(遥感旋转目标检测,全踩坑记录);

Usage Example

1. 'Get Dataset'

  • Split the DOTA_OBB image and labels. Trans DOTA format to YOLO longside format.

  • You can refer to hukaixuan19970627/DOTA_devkit_YOLO.

  • The Oriented YOLO Longside Format is:

$  classid    x_c   y_c   longside   shortside    Θ    Θ∈[0, 180)


* longside: The longest side of the oriented rectangle.

* shortside: The other side of the oriented rectangle.

* Θ: The angle between the longside and the x-axis(The x-axis rotates clockwise).x轴顺时针旋转遇到最长边所经过的角度

WARNING: IMAGE SIZE MUST MEETS 'HEIGHT = WIDTH'

2. 'train.py'

  • All same as ultralytics/yolov5. You better train demo files first before train your custom dataset.
  • Single GPU training:
$ python train.py  --batch-size 4 --device 0
  • Multi GPU training: DistributedDataParallel Mode
python -m torch.distributed.launch --nproc_per_node 4 train.py --sync-bn --device 0,1,2,3

train_batch_mosaic0 train_batch_mosaic1 train_batch_mosaic2

3. 'detect.py'

  • Download the demo files.
  • Then run the demo. Visualize the detection result and get the result txt files.
$  python detect.py

detection_result_before_merge1 detection_result_before_merge2 draw_detection_result

4. 'evaluation.py'

  • Run the detect.py demo first. Then change the path with yours:
evaluation
(
        detoutput=r'/....../DOTA_demo_view/detection',
        imageset=r'/....../DOTA_demo_view/row_images',
        annopath=r'/....../DOTA_demo_view/row_DOTA_labels/{:s}.txt'
)
draw_DOTA_image
(
        imgsrcpath=r'/...../DOTA_demo_view/row_images',
        imglabelspath=r'/....../DOTA_demo_view/detection/result_txt/result_merged',
        dstpath=r'/....../DOTA_demo_view/detection/merged_drawed'
)
  • Run the evaluation.py demo. Get the evaluation result and visualize the detection result which after merged.
$  python evaluation.py

detection_result_after_merge

有问题反馈

在使用中有任何问题,欢迎反馈给我,可以用以下联系方式跟我交流

  • 知乎(@略略略
  • 代码问题提issues,其他问题请知乎上联系

感激

感谢以下的项目,排名不分先后

关于作者

  Name  : "胡凯旋"
  describe myself:"咸鱼一枚"
  
Comments
  • Custom Dataset Question

    Custom Dataset Question

    1、我看到作者跟新后,使用了DATO格式的标签,但对于顺序的说明不是特别清楚(因为我是用rolabelIMG转成DATO的),是所有的旋转框/非旋转框都按照左上角顶点开始取四个点的位置吗? 2、我得到的DATO标签4个点虽然都是顺时针,但是起始顺序不是一致的,非旋转的label是从左上角开始的顺时针,但是有些旋转框的点是从右下角开始的,这种情况我是不是需要在计算四个点的时候加个180°?

    3、以下附上我训练配置的一些参数和结果(使用的预训练模型) image labels_correlogram labels_xyls P_curve PR_curve R_curve results train_batch0 train_batch6

    配置如下: image image

    opened by BandyKenny 22
  • windows: python setup.py develop出错

    windows: python setup.py develop出错

    nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2020 NVIDIA Corporation Built on Tue_Sep_15_19:12:04_Pacific_Daylight_Time_2020 Cuda compilation tools, release 11.1, V11.1.74 Build cuda_11.1.relgpu_drvr455TC455_06.29069683_0

    Tue Jan 11 17:00:56 2022 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 457.51 Driver Version: 457.51 CUDA Version: 11.1 | |-------------------------------+----------------------+----------------------+ | GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |===============================+======================+======================| | 0 GeForce RTX 306... WDDM | 00000000:26:00.0 On | N/A | | 0% 29C P8 9W / 200W | 350MiB / 8192MiB | 4% Default | | | | N/A | +-------------------------------+----------------------+----------------------+

    +-----------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=============================================================================| | 0 N/A N/A 1224 C+G Insufficient Permissions N/A | | 0 N/A N/A 1472 C+G ...8wekyb3d8bbwe\GameBar.exe N/A | | 0 N/A N/A 6404 C+G ...nputApp\TextInputHost.exe N/A | | 0 N/A N/A 6500 C+G ...bbwe\Microsoft.Photos.exe N/A | | 0 N/A N/A 6688 C+G C:\Windows\explorer.exe N/A | | 0 N/A N/A 8068 C+G ...5n1h2txyewy\SearchApp.exe N/A | | 0 N/A N/A 8660 C+G ...ekyb3d8bbwe\YourPhone.exe N/A | | 0 N/A N/A 10640 C+G ...8wekyb3d8bbwe\Cortana.exe N/A | | 0 N/A N/A 10784 C+G ...wekyb3d8bbwe\Video.UI.exe N/A | | 0 N/A N/A 10808 C+G ...y\ShellExperienceHost.exe N/A | | 0 N/A N/A 11876 C+G Insufficient Permissions N/A | | 0 N/A N/A 13552 C+G Insufficient Permissions N/A | | 0 N/A N/A 14676 C+G ...lPanel\SystemSettings.exe N/A | +-----------------------------------------------------------------------------+

    以下是错误信息

    (pytorch191) C:\Users\guowei\Desktop\yolov5_obb\utils\nms_rotated>python setup.py develop running develop running egg_info writing nms_rotated_ext.egg-info\PKG-INFO writing dependency_links to nms_rotated_ext.egg-info\dependency_links.txt writing top-level names to nms_rotated_ext.egg-info\top_level.txt D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\utils\cpp_extension.py:370: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back to using the slow distutils ba ckend. warnings.warn(msg.format('we could not find ninja.')) reading manifest file 'nms_rotated_ext.egg-info\SOURCES.txt' writing manifest file 'nms_rotated_ext.egg-info\SOURCES.txt' running build_ext D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\utils\cpp_extension.py:305: UserWarning: Error checking compiler version for cl: [WinError 2] 系统找不到指定的文件。 warnings.warn(f'Error checking compiler version for {compiler}: {error}') building '.nms_rotated_ext' extension C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\BIN\x86_amd64\cl.exe /c /nologo /Ox /W3 /GL /DNDEBUG /MD -DWITH_CUDA -ID:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include -ID:\ProgramData\Anaconda3\envs\p ytorch191\lib\site-packages\torch\include\torch\csrc\api\include -ID:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\TH -ID:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\THC "-IC:\Prog ram Files\NVIDIA GPU Computing Toolkit\CUDA\v11.1\include" -ID:\ProgramData\Anaconda3\envs\pytorch191\include -ID:\ProgramData\Anaconda3\envs\pytorch191\include "-IC:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\INCLUDE" "-IC :\Program Files (x86)\Windows Kits\10\include\10.0.10240.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\8.1\include\shared" "-IC:\Program Files (x86)\Windows Kits\8.1\include\um" "-IC:\Program Files (x86)\Windows Kits\8.1\include\wi nrt" /EHsc /Tpsrc/nms_rotated_cpu.cpp /Fobuild\temp.win-amd64-3.7\Release\src/nms_rotated_cpu.obj /MD /wd4819 /wd4251 /wd4244 /wd4267 /wd4275 /wd4018 /wd4190 /EHsc -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=nms_rotated_e xt -D_GLIBCXX_USE_CXX11_ABI=0 nms_rotated_cpu.cpp D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Array.h(111): warning C4814: 'c10::guts::array<_Tp,_Nm>::fill': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Array.h(232): note: see reference to class template instantiation 'c10::guts::array<_Tp,_Nm>' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Array.h(115): warning C4814: 'c10::guts::array<_Tp,_Nm>::swap': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Array.h(120): warning C4814: 'c10::guts::array<_Tp,_Nm>::begin': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Array.h(128): warning C4814: 'c10::guts::array<_Tp,_Nm>::end': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Array.h(136): warning C4814: 'c10::guts::array<_Tp,_Nm>::rbegin': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Array.h(144): warning C4814: 'c10::guts::array<_Tp,_Nm>::rend': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Array.h(182): warning C4814: 'c10::guts::array<_Tp,_Nm>::operator []': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'co nst' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Array.h(195): warning C4814: 'c10::guts::array<_Tp,_Nm>::at': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Array.h(210): warning C4814: 'c10::guts::array<_Tp,_Nm>::front': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Array.h(218): warning C4814: 'c10::guts::array<_Tp,_Nm>::back': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Array.h(227): warning C4814: 'c10::guts::array<_Tp,_Nm>::data': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/TypeList.h(405): error C2672: 'c10::guts::min': no matching overloaded function found D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/TypeList.h(408): note: see reference to class template instantiation 'c10::guts::typelist::drop_if_nonempty<TypeList,num>' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/TypeList.h(405): error C2782: 'const T &c10::guts::min(const T &,const T &)': template parameter 'T' is ambiguous D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/C++17.h(422): note: see declaration of 'c10::guts::min' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/TypeList.h(405): note: could be 'size::value' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/TypeList.h(405): note: or 'std::size_t' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/TypeList.h(405): error C2784: 'const T &c10::guts::min(const T &,const T &)': could not deduce template argument for 'const T &' from 'size: :value' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/C++17.h(422): note: see declaration of 'c10::guts::min' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/TypeList.h(407): error C2672: 'c10::guts::min': no matching overloaded function found D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/TypeList.h(407): error C2782: 'const T &c10::guts::min(const T &,const T &)': template parameter 'T' is ambiguous D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/C++17.h(422): note: see declaration of 'c10::guts::min' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/TypeList.h(407): note: could be 'size::value' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/TypeList.h(407): note: or 'std::size_t' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/TypeList.h(407): error C2784: 'const T &c10::guts::min(const T &,const T &)': could not deduce template argument for 'const T &' from 'size: :value' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/C++17.h(422): note: see declaration of 'c10::guts::min' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/DispatchKeySet.h(59): error C3250: '$L0': declaration is not allowed in 'constexpr' function body D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/DispatchKeySet.h(59): error C3249: illegal statement or sub-expression for 'constexpr' function D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/DispatchKeySet.h(59): error C3250: '$L0': declaration is not allowed in 'constexpr' function body D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/DispatchKeySet.h(59): error C3250: '$L0': declaration is not allowed in 'constexpr' function body D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/DispatchKeySet.h(59): note: see usage of '++' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/DispatchKeySet.h(59): error C3250: 'k': declaration is not allowed in 'constexpr' function body D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/DispatchKeySet.h(60): error C3249: illegal statement or sub-expression for 'constexpr' function D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/DispatchKeySet.h(60): note: see usage of '|=' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/DispatchKeySet.h(66): warning C4800: 'uint64_t': forcing value to bool 'true' or 'false' (performance warning) D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(177): warning C4814: 'c10::complex::operator =': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(299): note: see reference to class template instantiation 'c10::complex' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/DispatchKeySet.h(57): note: see reference to class template instantiation 'std::initializer_listc10::DispatchKey' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(182): warning C4814: 'c10::complex::operator +=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(187): warning C4814: 'c10::complex::operator -=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(193): warning C4814: 'c10::complex::operator *=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(199): warning C4814: 'c10::complex::operator /=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(206): warning C4814: 'c10::complex::operator =': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(213): warning C4814: 'c10::complex::operator +=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(220): warning C4814: 'c10::complex::operator -=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(232): warning C4814: 'c10::complex::operator *=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(251): warning C4814: 'c10::complex::operator /=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(259): warning C4814: 'c10::complex::operator =': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(292): warning C4814: 'c10::complex::real': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(298): warning C4814: 'c10::complex::imag': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(177): warning C4814: 'c10::complex::operator =': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(303): note: see reference to class template instantiation 'c10::complex' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(182): warning C4814: 'c10::complex::operator +=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const'

    D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(187): warning C4814: 'c10::complex::operator -=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const'

    D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(193): warning C4814: 'c10::complex::operator *=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const'

    D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(199): warning C4814: 'c10::complex::operator /=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const'

    D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(206): warning C4814: 'c10::complex::operator =': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(213): warning C4814: 'c10::complex::operator +=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const'

    D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(220): warning C4814: 'c10::complex::operator -=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const'

    D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(232): warning C4814: 'c10::complex::operator *=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const'

    D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(251): warning C4814: 'c10::complex::operator /=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const'

    D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(259): warning C4814: 'c10::complex::operator =': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(292): warning C4814: 'c10::complex::real': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(298): warning C4814: 'c10::complex::imag': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(177): warning C4814: 'c10::complex::operator =': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const'

    D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(307): note: see reference to class template instantiation 'c10::complex' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(182): warning C4814: 'c10::complex::operator +=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const ' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(187): warning C4814: 'c10::complex::operator -=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const ' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(193): warning C4814: 'c10::complex::operator *=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const ' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(199): warning C4814: 'c10::complex::operator /=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const ' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(206): warning C4814: 'c10::complex::operator =': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const'

    D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(213): warning C4814: 'c10::complex::operator +=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const ' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(220): warning C4814: 'c10::complex::operator -=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const ' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(232): warning C4814: 'c10::complex::operator *=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const ' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(251): warning C4814: 'c10::complex::operator /=': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const ' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(259): warning C4814: 'c10::complex::operator =': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const'

    D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(292): warning C4814: 'c10::complex::real': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/complex.h(298): warning C4814: 'c10::complex::imag': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(476): warning C4814: 'c10::optional::contained_val': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const'

    D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(688): note: see reference to class template instantiation 'c10::optional' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(479): warning C4814: 'c10::optional::contained_val': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const'

    D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(638): warning C4814: 'c10::optional::operator ->': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(647): warning C4814: 'c10::optional::operator *': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(652): warning C4814: 'c10::optional::operator *': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(664): warning C4814: 'c10::optional::value': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(670): warning C4814: 'c10::optional::value': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(682): warning C4814: 'c10::optional::value_or': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/Scalar.h(63): warning C4800: 'const int64_t': forcing value to bool 'true' or 'false' (performance warning) D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/Scalar.h(129): warning C4800: 'const int64_t': forcing value to bool 'true' or 'false' (performance warning) D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/reverse_iterator.h(92): warning C4814: 'c10::reverse_iterator<_Iterator>::operator =': in C++14 'constexpr' will not imply 'const'; consider explicitl y specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/reverse_iterator.h(176): note: see reference to class template instantiation 'c10::reverse_iterator<_Iterator>' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/reverse_iterator.h(125): warning C4814: 'c10::reverse_iterator<_Iterator>::operator ++': in C++14 'constexpr' will not imply 'const'; consider explici tly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/reverse_iterator.h(131): warning C4814: 'c10::reverse_iterator<_Iterator>::operator ++': in C++14 'constexpr' will not imply 'const'; consider explici tly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/reverse_iterator.h(136): warning C4814: 'c10::reverse_iterator<_Iterator>::operator --': in C++14 'constexpr' will not imply 'const'; consider explici tly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/reverse_iterator.h(142): warning C4814: 'c10::reverse_iterator<_Iterator>::operator --': in C++14 'constexpr' will not imply 'const'; consider explici tly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/reverse_iterator.h(151): warning C4814: 'c10::reverse_iterator<_Iterator>::operator +=': in C++14 'constexpr' will not imply 'const'; consider explici tly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/reverse_iterator.h(160): warning C4814: 'c10::reverse_iterator<_Iterator>::operator -=': in C++14 'constexpr' will not imply 'const'; consider explici tly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/string_view.h(59): warning C4814: 'c10::basic_string_view::operator =': in C++14 'constexpr' will not imply 'const'; consider explicitly specif ying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/string_view.h(642): note: see reference to class template instantiation 'c10::basic_string_view' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/string_view.h(160): warning C4814: 'c10::basic_string_view::remove_prefix': in C++14 'constexpr' will not imply 'const'; consider explicitly sp ecifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/string_view.h(169): warning C4814: 'c10::basic_string_view::remove_suffix': in C++14 'constexpr' will not imply 'const'; consider explicitly sp ecifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/string_view.h(175): warning C4814: 'c10::basic_string_view::swap': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/ConstexprCrc.h(103): error C3250: 'i': declaration is not allowed in 'constexpr' function body D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/ConstexprCrc.h(103): error C3249: illegal statement or sub-expression for 'constexpr' function D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/ConstexprCrc.h(103): note: see usage of '++' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/ConstexprCrc.h(104): error C3249: illegal statement or sub-expression for 'constexpr' function D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/ConstexprCrc.h(105): error C3249: illegal statement or sub-expression for 'constexpr' function D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/string_view.h(59): warning C4814: 'c10::basic_string_view::operator =': in C++14 'constexpr' will not imply 'const'; consider explicitly specify ing 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/ConstexprCrc.h(123): note: see reference to class template instantiation 'c10::basic_string_view' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/string_view.h(160): warning C4814: 'c10::basic_string_view::remove_prefix': in C++14 'constexpr' will not imply 'const'; consider explicitly spe cifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/string_view.h(169): warning C4814: 'c10::basic_string_view::remove_suffix': in C++14 'constexpr' will not imply 'const'; consider explicitly spe cifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/string_view.h(175): warning C4814: 'c10::basic_string_view::swap': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying ' const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(476): warning C4814: 'c10::optionalc10::ScalarType::contained_val': in C++14 'constexpr' will not imply 'const'; consider explicitly spec ifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/ScalarTypeToTypeMeta.h(30): note: see reference to class template instantiation 'c10::optionalc10::ScalarType' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2556: 'c10::ScalarType &c10::optionalc10::ScalarType::contained_val(void) const &': overloaded function differs only by retu rn type from 'const c10::ScalarType &c10::optionalc10::ScalarType::contained_val(void) const &' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalc10::ScalarType::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2373: 'c10::optionalc10::ScalarType::contained_val': redefinition; different type modifiers D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalc10::ScalarType::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(478): error C2059: syntax error: 'return' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(478): error C2238: unexpected token(s) preceding ';' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(481): error C2144: syntax error: 'void' should be preceded by ';' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(476): warning C4814: 'c10::optionalcaffe2::TypeMeta::contained_val': in C++14 'constexpr' will not imply 'const'; consider explicitly spe cifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/ScalarTypeToTypeMeta.h(30): note: see reference to class template instantiation 'c10::optionalcaffe2::TypeMeta' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2556: 'caffe2::TypeMeta &c10::optionalcaffe2::TypeMeta::contained_val(void) const &': overloaded function differs only by re turn type from 'const caffe2::TypeMeta &c10::optionalcaffe2::TypeMeta::contained_val(void) const &' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalcaffe2::TypeMeta::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2373: 'c10::optionalcaffe2::TypeMeta::contained_val': redefinition; different type modifiers D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalcaffe2::TypeMeta::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/ScalarTypeToTypeMeta.h(31): error C2039: 'has_value': is not a member of 'c10::optionalcaffe2::TypeMeta' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/ScalarTypeToTypeMeta.h(30): note: see declaration of 'c10::optionalcaffe2::TypeMeta' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/ScalarTypeToTypeMeta.h(32): error C2440: 'return': cannot convert from 'const c10::nullopt_t' to 'c10::optionalc10::ScalarType' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/ScalarTypeToTypeMeta.h(32): note: No constructor could take the source type, or constructor overload resolution was ambiguous D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/ScalarTypeToTypeMeta.h(34): error C2819: type 'c10::optionalcaffe2::TypeMeta' does not have an overloaded member 'operator ->' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/ScalarTypeToTypeMeta.h(30): note: see declaration of 'c10::optionalcaffe2::TypeMeta' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/ScalarTypeToTypeMeta.h(34): note: did you intend to use '.' instead? D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/ScalarTypeToTypeMeta.h(34): error C2039: 'toScalarType': is not a member of 'c10::optionalcaffe2::TypeMeta' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/ScalarTypeToTypeMeta.h(30): note: see declaration of 'c10::optionalcaffe2::TypeMeta' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(476): warning C4814: 'c10::optionalc10::Layout::contained_val': in C++14 'constexpr' will not imply 'const'; consider explicitly specifyi ng 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(36): note: see reference to class template instantiation 'c10::optionalc10::Layout' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2556: 'c10::Layout &c10::optionalc10::Layout::contained_val(void) const &': overloaded function differs only by return type from 'const c10::Layout &c10::optionalc10::Layout::contained_val(void) const &' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalc10::Layout::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2373: 'c10::optionalc10::Layout::contained_val': redefinition; different type modifiers D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalc10::Layout::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(37): error C2039: 'value_or': is not a member of 'c10::optionalc10::Layout' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(24): note: see declaration of 'c10::optionalc10::Layout' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(476): warning C4814: 'c10::optionalc10::Device::contained_val': in C++14 'constexpr' will not imply 'const'; consider explicitly specifyi ng 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(40): note: see reference to class template instantiation 'c10::optionalc10::Device' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2556: 'c10::Device &c10::optionalc10::Device::contained_val(void) const &': overloaded function differs only by return type from 'const c10::Device &c10::optionalc10::Device::contained_val(void) const &' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalc10::Device::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2373: 'c10::optionalc10::Device::contained_val': redefinition; different type modifiers D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalc10::Device::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(476): warning C4814: 'c10::optional::contained_val': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying 'con st' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(44): note: see reference to class template instantiation 'c10::optional' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2556: 'bool &c10::optional::contained_val(void) const &': overloaded function differs only by return type from 'const bo ol &c10::optional::contained_val(void) const &' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optional::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2373: 'c10::optional::contained_val': redefinition; different type modifiers D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optional::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(45): error C2039: 'value_or': is not a member of 'c10::optional' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(44): note: see declaration of 'c10::optional' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(148): error C2664: 'void c10::TensorOptions::set_layout(c10::optionalc10::Layout) noexcept &': cannot convert argument 1 from 'c10:: Layout' to 'c10::optionalc10::Layout' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(148): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(177): error C2664: 'void c10::TensorOptions::set_dtype(c10::optionalc10::ScalarType) noexcept &': cannot convert argument 1 from 'ca ffe2::TypeMeta' to 'c10::optionalcaffe2::TypeMeta' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(177): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(182): error C2664: 'void c10::TensorOptions::set_dtype(c10::optionalc10::ScalarType) noexcept &': cannot convert argument 1 from 'c1 0::ScalarType' to 'c10::optionalcaffe2::TypeMeta' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(182): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(476): warning C4814: 'c10::optionalc10::MemoryFormat::contained_val': in C++14 'constexpr' will not imply 'const'; consider explicitly sp ecifying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(187): note: see reference to class template instantiation 'c10::optionalc10::MemoryFormat' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2556: 'c10::MemoryFormat &c10::optionalc10::MemoryFormat::contained_val(void) const &': overloaded function differs only by return type from 'const c10::MemoryFormat &c10::optionalc10::MemoryFormat::contained_val(void) const &' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalc10::MemoryFormat::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2373: 'c10::optionalc10::MemoryFormat::contained_val': redefinition; different type modifiers D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalc10::MemoryFormat::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(187): error C2664: 'void c10::TensorOptions::set_memory_format(c10::optionalc10::MemoryFormat) noexcept &': cannot convert argument 1 from 'c10::MemoryFormat' to 'c10::optionalc10::MemoryFormat' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(187): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(287): error C2446: ':': no conversion from 'const c10::nullopt_t' to 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(287): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(308): error C2446: ':': no conversion from 'const c10::nullopt_t' to 'c10::optionalcaffe2::TypeMeta' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(308): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(324): error C2446: ':': no conversion from 'const c10::nullopt_t' to 'c10::optionalc10::Layout' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(324): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(341): error C2446: ':': no conversion from 'const c10::nullopt_t' to 'c10::optional' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(341): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(373): error C2446: ':': no conversion from 'const c10::nullopt_t' to 'c10::optional' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(373): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(388): error C2446: ':': no conversion from 'const c10::nullopt_t' to 'c10::optionalc10::MemoryFormat' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(388): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(429): error C2039: 'has_value': is not a member of 'c10::optionalc10::MemoryFormat' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(268): note: see declaration of 'c10::optionalc10::MemoryFormat' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(430): error C2100: illegal indirection D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(459): error C2451: conditional expression of type 'c10::optionalc10::Device' is illegal D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(459): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(460): error C2100: illegal indirection D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(469): error C2451: conditional expression of type 'c10::optionalcaffe2::TypeMeta' is illegal D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(469): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(470): error C2100: illegal indirection D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(479): error C2451: conditional expression of type 'c10::optionalc10::ScalarType' is illegal D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(479): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(480): error C2100: illegal indirection D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(489): error C2451: conditional expression of type 'c10::optionalc10::Layout' is illegal D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(489): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(490): error C2100: illegal indirection D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(490): error C2440: '=': cannot convert from 'c10::optionalc10::Layout' to 'c10::Layout' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(490): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(499): error C2451: conditional expression of type 'c10::optional' is illegal D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(499): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(500): error C2100: illegal indirection D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(500): error C2440: '=': cannot convert from 'c10::optional' to 'bool' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(500): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(509): error C2451: conditional expression of type 'c10::optional' is illegal D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(509): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(510): error C2100: illegal indirection D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(510): error C2440: '=': cannot convert from 'c10::optional' to 'bool' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(510): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(519): error C2451: conditional expression of type 'c10::optionalc10::MemoryFormat' is illegal D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(519): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(520): error C2100: illegal indirection D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(520): error C2440: '=': cannot convert from 'c10::optionalc10::MemoryFormat' to 'c10::MemoryFormat' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(520): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(568): error C2664: 'caffe2::TypeMeta c10::TensorOptions::dtype(void) noexcept const': cannot convert argument 1 from 'caffe2::TypeMeta ' to 'c10::optionalcaffe2::TypeMeta' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(568): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(573): error C2664: 'caffe2::TypeMeta c10::TensorOptions::dtype(void) noexcept const': cannot convert argument 1 from 'caffe2::TypeMeta ' to 'c10::optionalcaffe2::TypeMeta' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(573): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(579): error C2664: 'c10::Layout c10::TensorOptions::layout(void) noexcept const': cannot convert argument 1 from 'c10::Layout' to 'c10 ::optionalc10::Layout' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(579): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(597): error C2664: 'bool c10::TensorOptions::requires_grad(void) noexcept const': cannot convert argument 1 from 'bool' to 'c10::optio nal' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(597): note: No constructor could take the source type, or constructor overload resolution was ambiguous D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(603): error C2664: 'c10::TensorOptions c10::TensorOptions::memory_format(c10::optionalc10::MemoryFormat) noexcept const': cannot con vert argument 1 from 'c10::MemoryFormat' to 'c10::optionalc10::MemoryFormat' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(603): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(795): error C2664: 'c10::Layout c10::TensorOptions::layout(void) noexcept const': cannot convert argument 1 from 'c10::Layout' to 'c10 ::optionalc10::Layout' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(795): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(796): error C2228: left of '.device' must have class/struct/union D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(720): error C2039: 'has_value': is not a member of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(25): note: see declaration of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(722): error C2100: illegal indirection D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(722): error C2039: 'index': is not a member of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(25): note: see declaration of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(726): error C2039: 'has_value': is not a member of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(25): note: see declaration of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(728): error C2100: illegal indirection D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(1327): error C2039: 'has_value': is not a member of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(25): note: see declaration of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(1331): error C2100: illegal indirection D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(1331): error C2039: 'type': is not a member of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(25): note: see declaration of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(1562): error C2679: binary '=': no operator found which takes a right-hand operand of type 'c10::Device' (or there is no acceptable conve rsion) D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(479): note: could be 'c10::optionalc10::Device &c10::optionalc10::Device::operator =(c10::optionalc10::Device &&)' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(479): note: or 'c10::optionalc10::Device &c10::optionalc10::Device::operator =(const c10::optionalc10::Device &)' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(1562): note: while trying to match the argument list '(c10::optionalc10::Device, c10::Device)' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(1573): error C2679: binary '=': no operator found which takes a right-hand operand of type 'c10::Device' (or there is no acceptable conve rsion) D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(479): note: could be 'c10::optionalc10::Device &c10::optionalc10::Device::operator =(c10::optionalc10::Device &&)' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(479): note: or 'c10::optionalc10::Device &c10::optionalc10::Device::operator =(const c10::optionalc10::Device &)' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(1573): note: while trying to match the argument list '(c10::optionalc10::Device, c10::Device)' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(1637): error C2679: binary '=': no operator found which takes a right-hand operand of type 'c10::Device' (or there is no acceptable conve rsion) D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(479): note: could be 'c10::optionalc10::Device &c10::optionalc10::Device::operator =(c10::optionalc10::Device &&)' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(479): note: or 'c10::optionalc10::Device &c10::optionalc10::Device::operator =(const c10::optionalc10::Device &)' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(1637): note: while trying to match the argument list '(c10::optionalc10::Device, c10::Device)' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(1687): error C2679: binary '=': no operator found which takes a right-hand operand of type 'c10::Device' (or there is no acceptable conve rsion) D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(479): note: could be 'c10::optionalc10::Device &c10::optionalc10::Device::operator =(c10::optionalc10::Device &&)' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(479): note: or 'c10::optionalc10::Device &c10::optionalc10::Device::operator =(const c10::optionalc10::Device &)' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorImpl.h(1687): note: while trying to match the argument list '(c10::optionalc10::Device, c10::Device)' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/DeprecatedTypeProperties.h(99): error C2664: 'caffe2::TypeMeta c10::TensorOptions::dtype(void) noexcept const': cannot convert argument 1 from 'caffe 2::TypeMeta' to 'c10::optionalcaffe2::TypeMeta' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/DeprecatedTypeProperties.h(99): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be calle d D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/DeprecatedTypeProperties.h(100): error C2228: left of '.device' must have class/struct/union D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/DeprecatedTypeProperties.h(101): error C2228: left of '.layout' must have class/struct/union D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/DeprecatedTypeProperties.h(107): error C2039: 'has_value': is not a member of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(25): note: see declaration of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/DeprecatedTypeProperties.h(110): error C2039: 'value': is not a member of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/TensorOptions.h(25): note: see declaration of 'c10::optionalc10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/DeprecatedTypeProperties.h(110): error C2512: 'c10::Device': no appropriate default constructor available D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/Device.h(30): note: see declaration of 'c10::Device' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(476): warning C4814: 'c10::optionalat::TensorList::contained_val': in C++14 'constexpr' will not imply 'const'; consider explicitly speci fying 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/TensorBody.h(661): note: see reference to class template instantiation 'c10::optionalat::TensorList' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/core/MemoryFormat.h(63): note: see reference to class template instantiation 'c10::ArrayRef<int64_t>' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2556: 'at::TensorList &c10::optionalat::TensorList::contained_val(void) const &': overloaded function differs only by return type from 'const at::TensorList &c10::optionalat::TensorList::contained_val(void) const &' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalat::TensorList::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2373: 'c10::optionalat::TensorList::contained_val': redefinition; different type modifiers D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalat::TensorList::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/TensorBody.h(661): error C2440: 'default argument': cannot convert from 'const c10::nullopt_t' to 'c10::optionalat::TensorList' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/TensorBody.h(661): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/TensorBody.h(661): error C2440: 'default argument': cannot convert from 'const c10::nullopt_t' to 'c10::optional' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/TensorBody.h(661): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/TensorBody.h(734): error C2440: 'default argument': cannot convert from 'const c10::nullopt_t' to 'c10::optional' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/TensorBody.h(734): note: No user-defined-conversion operator available that can perform this conversion, or the operator cannot be called D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(183): warning C4624: 'c10::constexpr_storage_t': destructor was implicitly defined as deleted with [ T=at::Tensor ] D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(367): note: see reference to class template instantiation 'c10::constexpr_storage_t' being compiled with [ T=at::Tensor ] C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\INCLUDE\type_traits(487): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base' being compiled with [ T=at::Tensor ] C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\INCLUDE\type_traits(499): note: see reference to class template instantiation 'std::is_constructible<_Ty,const c10::trivially_copyable_optimization_optional_base &>' being co mpiled with [ _Ty=c10::trivially_copyable_optimization_optional_baseat::Tensor, T=at::Tensor ] D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(408): note: see reference to class template instantiation 'std::is_copy_constructible<c10::trivially_copyable_optimization_optional_base

    ' being compiled with [ T=at::Tensor ] D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(427): note: see reference to class template instantiation 'OptionalBaseat::Tensor' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/TensorBody.h(734): note: see reference to class template instantiation 'c10::optionalat::Tensor' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(395): warning C4624: 'c10::trivially_copyable_optimization_optional_base': destructor was implicitly defined as deleted with [ T=at::Tensor ] D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(476): warning C4814: 'c10::optionalat::Tensor::contained_val': in C++14 'constexpr' will not imply 'const'; consider explicitly specifyin g 'const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2556: 'at::Tensor &c10::optionalat::Tensor::contained_val(void) const &': overloaded function differs only by return type fr om 'const at::Tensor &c10::optionalat::Tensor::contained_val(void) const &' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalat::Tensor::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2373: 'c10::optionalat::Tensor::contained_val': redefinition; different type modifiers D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optionalat::Tensor::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(476): warning C4814: 'c10::optional<int64_t>::contained_val': in C++14 'constexpr' will not imply 'const'; consider explicitly specifying ' const' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\ATen/core/TensorBody.h(774): note: see reference to class template instantiation 'c10::optional<int64_t>' being compiled D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2556: 'int64_t &c10::optional<int64_t>::contained_val(void) const &': overloaded function differs only by return type from 'co nst int64_t &c10::optional<int64_t>::contained_val(void) const &' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optional<int64_t>::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): error C2373: 'c10::optional<int64_t>::contained_val': redefinition; different type modifiers D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(471): note: see declaration of 'c10::optional<int64_t>::contained_val' D:\ProgramData\Anaconda3\envs\pytorch191\lib\site-packages\torch\include\c10/util/Optional.h(477): fatal error C1003: error count exceeds 100; stopping compilation error: command 'C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\BIN\x86_amd64\cl.exe' failed with exit status 2

    opened by SSTato 18
  • nan in training

    nan in training

     第一个epoch训练到中间就直接变成nan,但是还在用nan训练,不知道问题在哪里
    Epoch   gpu_mem    box     obj        cls         theta    labels       img_size 
     0/119     6.51G     0.086    0.1064   0.04166    0.1764       186      1024:  81%|████████  | 2990/3683 [1:03:00<14:31,  1.26s/it]
     0/119     6.51G     0.086    0.1064   0.04166    0.1764       186      1024:  81%|████████  | 2991/3683 [1:03:00<14:32,  1.26s/it]
     0/119     6.51G     0.086    0.1064   0.04166    0.1764        93      1024:  81%|████████  | 2991/3683 [1:03:01<14:32,  1.26s/it]
     0/119     6.51G     0.086    0.1064   0.04166    0.1764        93      1024:  81%|████████  | 2992/3683 [1:03:01<14:46,  1.28s/it]
    

    突然就不对了 0/119 6.51G nan nan nan nan 220 1024: 81%|████████ | 2992/3683 [1:03:03<14:46, 1.28s/it] 0/119 6.51G nan nan nan nan 220 1024: 81%|████████▏ | 2993/3683 [1:03:03<14:36, 1.27s/it] 0/119 6.51G nan nan nan nan 88 1024: 81%|████████▏ | 2993/3683 [1:03:04<14:36, 1.27s/it] 0/119 6.51G nan nan nan nan 88 1024: 81%|████████▏ | 2994/3683 [1:03:04<14:12, 1.24s/it] 不知原因喃

    opened by LUO77123 17
  • (About mAP@0.5 on DOTAv1.5-testdev)关于mAP无法达到预期效果的问题

    (About [email protected] on DOTAv1.5-testdev)关于mAP无法达到预期效果的问题

    image mAP值总是在62左右徘徊,和67差了不少。detect方法采用分割的方法,取消了dataset的letterbox函数。具体代码:在 https://github.com/kuazhangxiaoai/Yolov5_OBB_Detection/blob/master/detect.py 以及 https://github.com/kuazhangxiaoai/Yolov5_OBB_Detection/blob/master/utils/datasets.py 请您帮我看一下,十分感谢胡大神。

    question Stale 
    opened by kuazhangxiaoai 14
  • nan in my custom dataset training

    nan in my custom dataset training

    训练时全是nan 训练集标签格式 image train_batch0 image train_batch1 image train_batch2 image 结果文件hyp.yaml lr0: 0.001 lrf: 0.2 momentum: 0.937 weight_decay: 0.0005 warmup_epochs: 3.0 warmup_momentum: 0.8 warmup_bias_lr: 0.1 box: 0.05 cls: 0.5 cls_pw: 1.0 theta: 0.5 theta_pw: 1.0 obj: 1.0 obj_pw: 1.0 iou_t: 0.2 anchor_t: 4.0 fl_gamma: 0.0 hsv_h: 0.015 hsv_s: 0.7 hsv_v: 0.4 degrees: 180.0 translate: 0.1 scale: 0.5 shear: 0.0 perspective: 0.0 flipud: 0.5 fliplr: 0.5 mosaic: 0.95 mixup: 0.1 copy_paste: 0.0 cls_theta: 180 csl_radius: 2.0 结果文件opt.yaml weights: weights\yolov5m.pt cfg: '' data: data\yolov5obb_demo.yaml hyp: data\hyps\obb\hyp.finetune_dota.yaml epochs: 10 batch_size: 1 imgsz: 1024 rect: false resume: false nosave: false noval: false noautoanchor: false evolve: null bucket: '' cache: null image_weights: false device: '0' multi_scale: false single_cls: false adam: false sync_bn: false workers: 8 project: runs\train name: exp exist_ok: false quad: false linear_lr: false label_smoothing: 0.0 patience: 100 freeze:

    • 0 save_period: -1 local_rank: -1 entity: null upload_dataset: false bbox_interval: -1 artifact_alias: latest save_dir: runs\train\exp
    opened by Mason1992-Git 13
  • evaluation

    evaluation

    when I used the evalution file for evaluation, I changed the following path to mine: classnames=['product'] classnames_inVal = ['0'] evaluation( detoutput='image_eval', imageset=r'/mnt/hdd10tb/Users/hoangnn/product/prj14_data_gen/DATA_26/GenProduct_Yolo_26_convert90_final/images/test/',annopath=r'/mnt/hdd10tb/Users/hoangnn/product/prj14_data_gen/DATA_26/GenProduct_Yolo_26_convert90_final/labels/test/{:s}.txt', classnames=classnames_inVal ) However, I have bugs related to not having a file: FileNotFoundError: [Errno 2] No such file or directory: 'image_eval/result_txt/result_classname/Task1_0.txt' I don't know what the folders: result_before_merge, result_merged, result_classname, result_txt are and I need to create them myself?

    opened by nhathoang0110 13
  • 【已顺利训练】Windows踩坑记录

    【已顺利训练】Windows踩坑记录

    好不容易装好了环境跑通了demo,看很多朋友都有windows运行的问题,分享一下我的踩坑(排坑)记录,希望有帮助。

    先检查: pytorch<=1.10(原因见issue #151 ) cuda和pytorch版本是否匹配 在命令行输入nvcc -V检查cuda是否可用,输入cl检查msvc是否可用(别的c++ compiler理论上也可以但我用的是这个) 正常输出: nvcc cl 确保这些所有就应该能够正常运行。以下是具体报错和解决办法。

    首先列出所有问题:

    1. OSError: CUDA_HOME environment variable is not set. Please set it to your CUDA install root.
    2. UserWarning: Error checking compiler version for cl: [WinError 2] 系统找不到指定的文件。(注意这个是cl,问题4是running build_ext)
    3. ImportError: cannot import name 'nms_rotated_ext' from partially initialized module 'utils.nms_rotated' (most likely due to a circular import)
    4. running build_ext error: [WinError 2] 系统找不到指定的文件。
    5. fatal error C1083: 无法打开包括文件: “THC/THC.h”: No such file or directory

    1. OSError: CUDA_HOME environment variable is not set. Please set it to your CUDA install root. 原因:没有安装cuda或cuda没有加入环境变量 解决:(临时解决)在命令行输入 set CUDA_HOME=/usr/local/cuda-X.X,建议搜索如何添加cuda到环境变量一劳永逸解决。 Ps. 我后来发现是cuda装在了anaconda里面,真实环境里根本没有cuda

    2. UserWarning: Error checking compiler version for cl: [WinError 2] 系统找不到指定的文件。 原因:没装msvc或者没有配置到环境变量 解决:如果没装MSVC或其她compiler,先安装;如果装好了依然报这个错,将cl.exe添加到path环境变量。配好之后在命令行输入cl,正常输出见开头。

    3. ImportError: cannot import name 'nms_rotated_ext' from partially initialized module 'utils.nms_rotated' (most likely due to a circular import) 原因:nms_rotated_ext是从yolov5_obb-master\utils\nms_rotated\src里面的cpp或cu文件编译过来的,需要先进行编译,python才能读懂。因为编码问题,poly_nms_cuda.cu那个文件需要换成 #224 中的版本。 解决:在命令行cd utils\nms_rotated转到setup.py所在的文件夹,然后输入python setup.py develop

    4. running build_ext error: [WinError 2] 系统找不到指定的文件。 原因:msvc或cuda compiler不可用 解决:重装。验证msvc:命令行输入cl;验证cuda:命令行输入nvcc -V

    5. fatal error C1083: 无法打开包括文件: “THC/THC.h”: No such file or directory 原因:见 #151 ,pytorch>=1.11弃用了一些文件,请使用pytorch<=1.10,我用的是1.10.2(和cuda11.3) 题外话:装cuda和pytorch花了很长时间,torch官网没有1.10.2的命令,我尝试装1.10.0和1.10.1,运行detect的时候报错CUDA version (11.3) mismatches the version that was used to compile PyTorch (10.2),最后输入conda install pytorch==1.10.2 torchvision torchaudio cudatoolkit=11.3 装好了(记得换清华源

    opened by xwxmars 11
  • mAP Question about Custom Dataset

    mAP Question about Custom Dataset

    想请教下,我的为什么训练出来是这样的 results.png image train_batch0.jpg image train_batch1.jpg image train_batch2.jpg image train_batch3.jpg image val_batch0_labels.jpg image val_batch1_labels.jpg image @hukaixuan19970627 @sunbuhui @Ethan-niu

    opened by Hone-Xu 11
  • final format

    final format

    您好作者。 def poly2rbox_single(poly): """ poly:[x0,y0,x1,y1,x2,y2,x3,y3] to rrect:[x_ctr,y_ctr,w,h,angle] 这个代码是将四点坐标的poly转为x_ctr,y_ctr,w,h,angle格式,我有点疑惑,就是您这个转换貌似最后return的并没有进行归一化,这样输入到yolo网络应该是不行的。或者是您在poly:[x0,y0,x1,y1,x2,y2,x3,y3]做了归一化吗?所以转为rrect:[x_ctr,y_ctr,w,h,angle]就不需要再做归一化了?

    opened by shining-love 11
  • 是否可以支持中文标签?

    是否可以支持中文标签?

    采用中文标签,在csdn上其他博主的中文标签更改步骤走了一遍,仍然报错不能识别中文标签

    train: WARNING: D:\py\yolov5_obb\mydata\images\381.jpeg: ignoring corrupt image/label: 'L型扳手' is not in list train: WARNING: D:\py\yolov5_obb\mydata\images\382.jpeg: ignoring corrupt image/label: 'L型扳手' is not in list train: WARNING: D:\py\yolov5_obb\mydata\images\383.jpeg: ignoring corrupt image/label: 'L型扳手' is not in list train: WARNING: D:\py\yolov5_obb\mydata\images\384.jpeg: ignoring corrupt image/label: 'L型扳手' is not in list train: WARNING: D:\py\yolov5_obb\mydata\images\385.jpeg: ignoring corrupt image/label: 'L型扳手' is not in list

    opened by aniseanise 0
  • Custom Dataset Training

    Custom Dataset Training

    相关设置.docx 博主您好,想请教一下用自制数据集进行训练的问题,我的数据是每张图单个大目标,根据其他issue关闭了mosaic,patience为300。相关设置整理在doc文档,数据应该够的,因为在Yolov5不是旋转框的版本上训练过,效果不错,预测概率均为0.9左右,但在obb中表现不是太好,预测概率很低,部分预测不出框,想请教一下应该怎么样调参,十分感谢!

    opened by Dhasii 0
  • fix val.py bug

    fix val.py bug

    I found create_dataloader function param names variable type is list, but in val.py line 161

    names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.names)}
    

    now names is a dict, this will make error if you didn't train A dataset before, if you train A dataset before, it will create label cache and create_dataloader will load label cache, no errors will occur. maybe it in line 167, it can change to

    dataloader = create_dataloader(data[task], imgsz, batch_size, stride, list(names.values()), single_cls, pad=pad, rect=pt,
                                           workers=workers, prefix=colorstr(f'{task}: '))[0]
    
    opened by regainOWO 0
  • 检测目标不完整和检测不到的问题

    检测目标不完整和检测不到的问题

    作者您好,我基于本项目训练条码和二维码的旋转目标检测,我大概准备了108张图片,然后每天图片按5度旋转生成总数7776张的图片,其中训练集占6220张,验证集占1556张,数据增强那里只关闭mosaic,其它的没有变改,做了1000 epoch训训练,训练结果如图所示 train_batch0 train_batch1 train_batch2 train_batch3 train_batch4 train_batch5 train_batch6 train_batch7 val_batch0_labels val_batch0_pred val_batch1_labels val_batch1_pred val_batch2_labels val_batch2_pred results 在实际检测当中,针对长的条码,容易检测不全,短的条码容易检测不出来(已经把置信度开个了平方根,并且设置0.3的置信度) QQ截图20221226101931 能否提供一下后续改进的思路?

    opened by hf62580 3
  • Inference via torch.hub

    Inference via torch.hub

    Hello guys, I want to use my custom trained model via torch.hub. I load the model like follows:

    model = torch.hub.load(source='local', repo_or_dir=r'path\to\local\yolov5_obb', model='custom', path=r'./model/yolov5_obb_best.pt')

    The thing is I always get the ERROR:

    ImportError: cannot import name 'nms_rotated_ext' from partially initialized module 'utils.nms_rotated' (most likely due to a circular import)

    The compliation of nms_rotated was successful. I saw that there where some other issues regarding to that ERROR, but since the complilation was successful I guess there is another issue.

    By the way I'm using Windows 10, PyTorch 1.9, CUDA 11.4 and the detect.py is working perfectly fine.

    Maybe someone could help me solve this issue.

    Thanks in advance.

    opened by StaHRocK1992 0
Owner
null
Source code of RRPN ---- Arbitrary-Oriented Scene Text Detection via Rotation Proposals

Paper source Arbitrary-Oriented Scene Text Detection via Rotation Proposals https://arxiv.org/abs/1703.01086 News We update RRPN in pytorch 1.0! View

null 428 Nov 22, 2022
Deskew is a command line tool for deskewing scanned text documents. It uses Hough transform to detect "text lines" in the image. As an output, you get an image rotated so that the lines are horizontal.

Deskew by Marek Mauder https://galfar.vevb.net/deskew https://github.com/galfar/deskew v1.30 2019-06-07 Overview Deskew is a command line tool for des

Marek Mauder 127 Dec 3, 2022
This project modify tensorflow object detection api code to predict oriented bounding boxes. It can be used for scene text detection.

This is an oriented object detector based on tensorflow object detection API. Most of the code is not changed except for those related to the need of

Dafang He 30 Oct 22, 2022
The code for “Oriented RepPoints for Aerail Object Detection”

Oriented RepPoints for Aerial Object Detection The code for the implementation of “Oriented RepPoints”, Under review. (arXiv preprint) Introduction Or

WentongLi 207 Dec 24, 2022
Motion detector, Full body detection, Upper body detection, Cat face detection, Smile detection, Face detection (haar cascade), Silverware detection, Face detection (lbp), and Sending email notifications

Security camera running OpenCV for object and motion detection. The camera will send email with image of any objects it detects. It also runs a server that provides web interface with live stream video.

Peace 10 Jun 30, 2021
An Implementation of the alogrithm in paper IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection

InceptText-Tensorflow An Implementation of the alogrithm in paper IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Orien

GeorgeJoe 115 Dec 12, 2022
Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation

This is the official implementation of "Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation". For more details, please

Pengyuan Lyu 309 Dec 6, 2022
An Implementation of the seglink alogrithm in paper Detecting Oriented Text in Natural Images by Linking Segments

Tips: A more recent scene text detection algorithm: PixelLink, has been implemented here: https://github.com/ZJULearning/pixel_link Contents: Introduc

dengdan 484 Dec 7, 2022
An Implementation of the FOTS: Fast Oriented Text Spotting with a Unified Network

FOTS: Fast Oriented Text Spotting with a Unified Network Introduction This is a pytorch re-implementation of FOTS: Fast Oriented Text Spotting with a

GeorgeJoe 171 Aug 4, 2022
TensorFlow Implementation of FOTS, Fast Oriented Text Spotting with a Unified Network.

FOTS: Fast Oriented Text Spotting with a Unified Network I am still working on this repo. updates and detailed instructions are coming soon! Table of

Masao Taketani 52 Nov 11, 2022
TextBoxes++: A Single-Shot Oriented Scene Text Detector

TextBoxes++: A Single-Shot Oriented Scene Text Detector Introduction This is an application for scene text detection (TextBoxes++) and recognition (CR

Minghui Liao 930 Jan 4, 2023
Total Text Dataset. It consists of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.

Total-Text-Dataset (Official site) Updated on April 29, 2020 (Detection leaderboard is updated - highlighted E2E methods. Thank you shine-lcy.) Update

Chee Seng Chan 671 Dec 27, 2022
A novel region proposal network for more general object detection ( including scene text detection ).

DeRPN: Taking a further step toward more general object detection DeRPN is a novel region proposal network which concentrates on improving the adaptiv

Deep Learning and Vision Computing Lab, SCUT 151 Dec 12, 2022
Morphological edge detection or object's boundary detection using erosion and dialation in OpenCV python

Morphologycal-edge-detection-using-erosion-and-dialation the task is to detect object boundary using erosion or dialation . Here, use the kernel or st

Tamzid hasan 3 Nov 25, 2022
(CVPR 2021) Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds

BRNet Introduction This is a release of the code of our paper Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds,

null 86 Oct 5, 2022
Scale-aware Automatic Augmentation for Object Detection (CVPR 2021)

SA-AutoAug Scale-aware Automatic Augmentation for Object Detection Yukang Chen, Yanwei Li, Tao Kong, Lu Qi, Ruihang Chu, Lei Li, Jiaya Jia [Paper] [Bi

Jia Research Lab 182 Dec 29, 2022
(CVPR 2021) ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection

ST3D Code release for the paper ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection, CVPR 2021 Authors: Jihan Yang*, Shaoshu

CVMI Lab 224 Dec 28, 2022
OCR, Object Detection, Number Plate, Real Time

README.md PrePareded anaconda env requirements.txt clova AI → deep text recognition → trained weights (ex, .pth) wpod-net weights (ex, .h5 , .json) ht

Kaven Lee 7 Dec 6, 2022
deployment of a hybrid model for automatic weapon detection/ anomaly detection for surveillance applications

Automatic Weapon Detection Deployment of a hybrid model for automatic weapon detection/ anomaly detection for surveillance applications. Loved the pro

Janhavi 4 Mar 4, 2022