ifzhang / fairmot

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

Hi there 👋

fairmot's Issues

Posetrack dataset

Have you tried to test the performance on the Posetrack dataset? I think that it could be test with another head extension.

About Speed

你好，请问咱们的30fps是在2080显卡上测试的吗？有没有在cpu上的测试速度呢？
还有就是咱们的模型有百度云的吗？您上传的链接链接不上

Multitask learning with uncertainty ?

Here, it looks like that the uncertainty is used to learn multitask.

BUT, I can NOT find that the parameters is updated by any optimizer ...
I just found that the instance of loss is made here.

Could you point out where the uncertainty is learned during training?

Running on cpu system

Hi,

Thanks for your great work. I have a question can i run this algorithm on CPU machine if i modify few of the code.

Thanks in Advance.

When i started from the beginning, i get a error

RuntimeError: invalid argument 2: non-empty vector or matrix expected at /tmp/pip-req-build-58y_cjjl/aten/src/THCUNN/generic/ClassNLLCriterion.cu:31
i just change the input size.
please, can you help me ?

your model does not fully load the pre-trained weight.

I try model only with MOT15 dataset

When I run sh experiments/all_dla34.sh I got this info。

Is that normal?

*nvaild command name 'develop

When I try to sh make,sh in DVNv2.This error appear. How to solve it?

ValueError: unsupported pickle protocol: 59

When I tried to run 'sh experiments/all_dla34.sh', it comes to the error:
Traceback (most recent call last):
File "train.py", line 97, in
main(opt)
File "train.py", line 43, in main
model = create_model(opt.arch, opt.heads, opt.head_conv)
File "/home/huanzhang/code/fairmot/src/lib/models/model.py", line 25, in create_model
model = get_model(num_layers=num_layers, heads=heads, head_conv=head_conv)
File "/home/huanzhang/code/fairmot/src/lib/models/networks/pose_dla_dcn.py", line 490, in get_pose_net
head_conv=head_conv)
File "/home/huanzhang/code/fairmot/src/lib/models/networks/pose_dla_dcn.py", line 433, in init
self.base = globals()base_name
File "/home/huanzhang/code/fairmot/src/lib/models/networks/pose_dla_dcn.py", line 313, in dla34
model.load_pretrained_model(data='imagenet', name='dla34', hash='ba72cf86')
File "/home/huanzhang/code/fairmot/src/lib/models/networks/pose_dla_dcn.py", line 299, in load_pretrained_model
model_weights = model_zoo.load_url(model_url)
File "/home/huanzhang/anaconda3/envs/fairmot/lib/python3.7/site-packages/torch/hub.py", line 463, in load_state_dict_from_url
return torch.load(cached_file, map_location=map_location)
File "/home/huanzhang/anaconda3/envs/fairmot/lib/python3.7/site-packages/torch/serialization.py", line 386, in load
return _load(f, map_location, pickle_module, **pickle_load_args)
File "/home/huanzhang/anaconda3/envs/fairmot/lib/python3.7/site-packages/torch/serialization.py", line 563, in _load
magic_number = pickle_module.load(f, **pickle_load_args)
ValueError: unsupported pickle protocol: 59

Could you help me to solve this? THX~

Could you share the instruction about both detect and re-id?

Thanks for your great work!
I new to MOT, could you please share the instruction about both detect and re-id?
I only find the process about how to do tracking test, but I wonder how to do both detect test and tracking test?
By the way, I wonder how you generate the seqinfo.ini files?

How to speed up execution?

I have successfully ran the demo script and made the example used in the README file by myself.
But the speed is slow, it's around 2-3 FPS.

How can I speed up this number?

Build error

win10
Anaconda3
python3.7.6

when I input "pip install -r requirements.txt",there are some errors. The details are as follows:
Building wheel for cython-bbox (setup.py) ... error
ERROR: Command errored out with exit status 1:
command: 'C:\Users\wangy\anaconda3\python.exe' -u -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'C:\Users\wangy\AppData\Local\Temp\pip-install-ph7atx1f\cython-bbox\setup.py'"'"'; file='"'"'C:\Users\wangy\AppData\Local\Temp\pip-install-ph7atx1f\cython-bbox\setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(file);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, file, '"'"'exec'"'"'))' bdist_wheel -d 'C:\Users\wangy\AppData\Local\Temp\pip-wheel-4v893r3g'
cwd: C:\Users\wangy\AppData\Local\Temp\pip-install-ph7atx1f\cython-bbox
Complete output (11 lines):
running bdist_wheel
running build
running build_ext
building 'cython_bbox' extension
creating build
creating build\temp.win-amd64-3.7
creating build\temp.win-amd64-3.7\Release
creating build\temp.win-amd64-3.7\Release\src
C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\BIN\x86_amd64\cl.exe /c /nologo /Ox /W3 /GL /DNDEBUG /MD -IC:\Users\wangy\anaconda3\lib\site-packages\numpy\core\include -IC:\Users\wangy\anaconda3\include -IC:\Users\wangy\anaconda3\include "-IC:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\INCLUDE" "-IC:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\ATLMFC\INCLUDE" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.10150.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.6\include\um" "-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\winrt" /Tcsrc/cython_bbox.c /Fobuild\temp.win-amd64-3.7\Release\src/cython_bbox.obj -Wno-cpp
cl: 命令行 error D8021 :无效的数值参数“/Wno-cpp”
error: command 'C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\BIN\x86_amd64\cl.exe' failed with exit status 2

ERROR: Failed building wheel for cython-bbox
I I tried some methods, but I still couldn't work it out. So I really want to get some guidance. Thank you very much

error in modulated_deformable_im2col_cuda: invalid device function

When I run demo.py to test my video, I get the message that error in modulated_deformable_im2col_cuda: invalid device function. How to solve it?

Performance in presence of occlusions

Can the model also track objects (people) in case of occlusions ? I have tried Deepsort but tracked IDs used to change as soon as the object gets occluded and reappears

download paper from http://cn.arxiv.org/pdf/2004.01888.pdf fail

最近几天从arxiv下载您的大作总失败， 您能否发我一份？(QQ:[email protected])

ModuleNotFoundError

win10
I have installed all the requirements.
When I input "python F:\soft\FairMOT-master\src\demo.py ",there are following errors:
ModuleNotFoundError: No module named '_ext';

So I input" python F:\soft\FairMOT-master\src\lib\models\networks\DCNv2\setup.py build develop",there are also some errors.The errors are as follows:
c:\users\admin\anaconda3\lib\site-packages\torch\include\pybind11\detail/common.h(71): fatal error C1189: #error: pybind11 requires MSVC 2015 update 3 or newer
error: command 'C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\BIN\x86_amd64\cl.exe' failed with exit status 2.
I hope to get some guidance,thank you very much.

I have a confusion about the details of the paper?

From Table 2, ResNet-50 means resnet50+fpn+dcn， and samely all model default have dcn?
Is my understanding correct？ Thank you ！

not fully load the pre-trained weights, Is this normal?, when I run the shell command "python train.py ***",

model maybe corrupted when I run training or demo.

Hello, I downloaded your models as your point. But when I train or run demo they show as follow:
RuntimeError: unexpected EOF, expected 1132938 more bytes. The file might be corrupted.
I tried the solution searched on Google, but not solved.

How to solve it? Thank you.

The training terminal output as follow:

`Traceback (most recent call last):
File "train.py", line 97, in
main(opt)
File "train.py", line 43, in main
model = create_model(opt.arch, opt.heads, opt.head_conv)
File "/media/lalalademaxiya/FairMOT/src/lib/models/model.py", line 25, in create_model
model = get_model(num_layers=num_layers, heads=heads, head_conv=head_conv)
File "/media/lalalademaxiya/FairMOT/src/lib/models/networks/pose_dla_dcn.py", line 490, in get_pose_net
head_conv=head_conv)
File "/media/lalalademaxiya/FairMOT/src/lib/models/networks/pose_dla_dcn.py", line 433, in init
self.base = globals()base_name
File "/media/lalalademaxiya/FairMOT/src/lib/models/networks/pose_dla_dcn.py", line 313, in dla34
model.load_pretrained_model(data='imagenet', name='dla34', hash='ba72cf86')
File "/media/lalalademaxiya/FairMOT/src/lib/models/networks/pose_dla_dcn.py", line 299, in load_pretrained_model
model_weights = model_zoo.load_url(model_url)
File "/home/XXX/.local/lib/python3.6/site-packages/torch/hub.py", line 506, in load_state_dict_from_url
return torch.load(cached_file, map_location=map_location)
File "/home/XXX/.local/lib/python3.6/site-packages/torch/serialization.py", line 529, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "/home/XXX/.local/lib/python3.6/site-packages/torch/serialization.py", line 709, in _legacy_load
deserialized_objects[key].set_from_file(f, offset, f_should_read_directly)
RuntimeError: unexpected EOF, expected 1132938 more bytes. The file might be corrupted.
terminate called after throwing an instance of 'c10::Error'
what(): owning_ptr == NullType::singleton() || owning_ptr->refcount.load() > 0 INTERNAL ASSERT FAILED at /pytorch/c10/util/intrusive_ptr.h:348, please report a bug to PyTorch. intrusive_ptr: Can only intrusive_ptr::reclaim() owning pointers that were created using intrusive_ptr::release(). (reclaim at /pytorch/c10/util/intrusive_ptr.h:348)
frame #0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x33 (0x7fd0e4588193 in /home/XXX/.local/lib/python3.6/site-packages/torch/lib/libc10.so)
frame #1: + 0x18cd59f (0x7fd08083259f in /home/XXX/.local/lib/python3.6/site-packages/torch/lib/libtorch.so)
frame #2: THStorage_free + 0x17 (0x7fd080ffaba7 in /home/XXX/.local/lib/python3.6/site-packages/torch/lib/libtorch.so)
frame #3: + 0x55d65d (0x7fd0e784965d in /home/XXX/.local/lib/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #4: python3() [0x54f6e6]
frame #5: python3() [0x5734e0]
frame #6: python3() [0x4b1a28]
frame #7: python3() [0x589078]
frame #8: python3() [0x5ade68]
frame #9: python3() [0x5ade7e]
frame #10: python3() [0x5ade7e]
frame #11: python3() [0x5ade7e]
frame #12: python3() [0x5ade7e]
frame #13: python3() [0x5ade7e]
frame #14: python3() [0x5ade7e]
frame #15: python3() [0x5ade7e]
frame #16: python3() [0x5ade7e]
frame #17: python3() [0x5ade7e]
frame #18: python3() [0x56be56]

frame #24: __libc_start_main + 0xe7 (0x7fd0ecc45b97 in /lib/x86_64-linux-gnu/libc.so.6)

Aborted (core dumped)`

CUDA9

IR Detection

Really great work.....
But i have faced an issue, the person detection part does not work on IR images/videos...
So can you help me here?
Thank You

How to get the offline results?

Hello, thanks for your great work!
It is mentioned in the paper that your tracker also achieves the highest MOTA score among all online and offline trackers. And in this repo, the code seems could get only online results. Am I right?
And to get the offline results, how do I modify the code?

Build errors

I am failing at the last command from the installation description https://github.com/ifzhang/FairMOT#installation

Which version of GCC do I need to use?

The log:

(FairMOT) yehor@desktop:~/Work/YehorSmoliakov/FairMOT-DEMO/FairMOT/src/lib/models/networks/DCNv2$ python setup.py build develop
running build
running build_ext
building '_ext' extension
gcc -pthread -B /home/yehor/Tools/anaconda3/envs/FairMOT/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/yehor/Work/YehorSmoliakov/FairMOT-DEMO/FairMOT/src/lib/models/networks/DCNv2/src -I/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include -I/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/TH -I/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/THC -I/home/yehor/Tools/anaconda3/envs/FairMOT/include/python3.7m -c /home/yehor/Work/YehorSmoliakov/FairMOT-DEMO/FairMOT/src/lib/models/networks/DCNv2/src/vision.cpp -o build/temp.linux-x86_64-3.7/home/yehor/Work/YehorSmoliakov/FairMOT-DEMO/FairMOT/src/lib/models/networks/DCNv2/src/vision.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_ext -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
gcc -pthread -B /home/yehor/Tools/anaconda3/envs/FairMOT/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/yehor/Work/YehorSmoliakov/FairMOT-DEMO/FairMOT/src/lib/models/networks/DCNv2/src -I/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include -I/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/TH -I/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/THC -I/home/yehor/Tools/anaconda3/envs/FairMOT/include/python3.7m -c /home/yehor/Work/YehorSmoliakov/FairMOT-DEMO/FairMOT/src/lib/models/networks/DCNv2/src/cpu/dcn_v2_cpu.cpp -o build/temp.linux-x86_64-3.7/home/yehor/Work/YehorSmoliakov/FairMOT-DEMO/FairMOT/src/lib/models/networks/DCNv2/src/cpu/dcn_v2_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_ext -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
/usr/bin/nvcc -DWITH_CUDA -I/home/yehor/Work/YehorSmoliakov/FairMOT-DEMO/FairMOT/src/lib/models/networks/DCNv2/src -I/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include -I/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/TH -I/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/THC -I/home/yehor/Tools/anaconda3/envs/FairMOT/include/python3.7m -c /home/yehor/Work/YehorSmoliakov/FairMOT-DEMO/FairMOT/src/lib/models/networks/DCNv2/src/cuda/dcn_v2_cuda.cu -o build/temp.linux-x86_64-3.7/home/yehor/Work/YehorSmoliakov/FairMOT-DEMO/FairMOT/src/lib/models/networks/DCNv2/src/cuda/dcn_v2_cuda.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DCUDA_HOST_COMPILER=/usr/bin/gcc-7 -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_ext -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor}]’:
/usr/include/c++/6/tuple:626:248:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (3ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor>}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (3ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/core/TensorMethods.h:1566:176:   required from here
/usr/include/c++/6/tuple:483:67: error: mismatched argument pack lengths while expanding ‘std::is_constructible<_Elements, _UElements&&>’
       return __and_<is_constructible<_Elements, _UElements&&>...>::value;
                                                                   ^~~~~
/usr/include/c++/6/tuple:484:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor}]’:
/usr/include/c++/6/tuple:626:362:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (3ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor>}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (3ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/core/TensorMethods.h:1566:176:   required from here
/usr/include/c++/6/tuple:489:65: error: mismatched argument pack lengths while expanding ‘std::is_convertible<_UElements&&, _Elements>’
       return __and_<is_convertible<_UElements&&, _Elements>...>::value;
                                                                 ^~~~~
/usr/include/c++/6/tuple:490:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor, at::Tensor, at::Tensor>&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor}]’:
/usr/include/c++/6/tuple:662:419:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor>::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(const std::tuple<_Args1 ...>&) [with _UElements = {at::Tensor, at::Tensor, at::Tensor}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor>::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/core/TensorMethods.h:1566:176:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (4, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor, at::Tensor, at::Tensor>&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor, at::Tensor, at::Tensor>&&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor}]’:
/usr/include/c++/6/tuple:686:422:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor>::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(std::tuple<_Args1 ...>&&) [with _UElements = {at::Tensor, at::Tensor, at::Tensor}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor>::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/core/TensorMethods.h:1566:176:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (4, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor, at::Tensor, at::Tensor>&&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’:
/usr/include/c++/6/tuple:626:248:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (5ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (5ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1209:5:   required from here
/usr/include/c++/6/tuple:483:67: error: mismatched argument pack lengths while expanding ‘std::is_constructible<_Elements, _UElements&&>’
       return __and_<is_constructible<_Elements, _UElements&&>...>::value;
                                                                   ^~~~~
/usr/include/c++/6/tuple:484:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’:
/usr/include/c++/6/tuple:626:362:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (5ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (5ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1209:5:   required from here
/usr/include/c++/6/tuple:489:65: error: mismatched argument pack lengths while expanding ‘std::is_convertible<_UElements&&, _Elements>’
       return __and_<is_convertible<_UElements&&, _Elements>...>::value;
                                                                 ^~~~~
/usr/include/c++/6/tuple:490:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’:
/usr/include/c++/6/tuple:662:419:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(const std::tuple<_Args1 ...>&) [with _UElements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1209:5:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (6, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>&&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’:
/usr/include/c++/6/tuple:686:422:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(std::tuple<_Args1 ...>&&) [with _UElements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1209:5:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (6, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor>&&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> >}]’:
/usr/include/c++/6/tuple:626:248:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1214:54:   required from here
/usr/include/c++/6/tuple:483:67: error: mismatched argument pack lengths while expanding ‘std::is_constructible<_Elements, _UElements&&>’
       return __and_<is_constructible<_Elements, _UElements&&>...>::value;
                                                                   ^~~~~
/usr/include/c++/6/tuple:484:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> >}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> >}]’:
/usr/include/c++/6/tuple:626:362:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1214:54:   required from here
/usr/include/c++/6/tuple:489:65: error: mismatched argument pack lengths while expanding ‘std::is_convertible<_UElements&&, _Elements>’
       return __and_<is_convertible<_UElements&&, _Elements>...>::value;
                                                                 ^~~~~
/usr/include/c++/6/tuple:490:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> >}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> >}]’:
/usr/include/c++/6/tuple:662:419:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(const std::tuple<_Args1 ...>&) [with _UElements = {at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> >}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1214:54:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (5, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> >}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >&&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> >}]’:
/usr/include/c++/6/tuple:686:422:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(std::tuple<_Args1 ...>&&) [with _UElements = {at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> >}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1214:54:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (5, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> > >&&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, std::vector<at::Tensor, std::allocator<at::Tensor> >}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, long int>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, long int}]’:
/usr/include/c++/6/tuple:626:248:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, long int>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, long int>}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, long int>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1475:343:   required from here
/usr/include/c++/6/tuple:483:67: error: mismatched argument pack lengths while expanding ‘std::is_constructible<_Elements, _UElements&&>’
       return __and_<is_constructible<_Elements, _UElements&&>...>::value;
                                                                   ^~~~~
/usr/include/c++/6/tuple:484:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, long int>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, long int}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, long int>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, long int}]’:
/usr/include/c++/6/tuple:626:362:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, long int>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, long int>}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, long int>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1475:343:   required from here
/usr/include/c++/6/tuple:489:65: error: mismatched argument pack lengths while expanding ‘std::is_convertible<_UElements&&, _Elements>’
       return __and_<is_convertible<_UElements&&, _Elements>...>::value;
                                                                 ^~~~~
/usr/include/c++/6/tuple:490:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, long int>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, long int}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor, at::Tensor, at::Tensor, long int>&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, long int}]’:
/usr/include/c++/6/tuple:662:419:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, long int>::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(const std::tuple<_Args1 ...>&) [with _UElements = {at::Tensor, at::Tensor, at::Tensor, long int}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, long int>::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1475:343:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (5, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor, at::Tensor, at::Tensor, long int>&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, long int}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor, at::Tensor, at::Tensor, long int>&&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, long int}]’:
/usr/include/c++/6/tuple:686:422:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, long int>::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(std::tuple<_Args1 ...>&&) [with _UElements = {at::Tensor, at::Tensor, at::Tensor, long int}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, long int>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, long int>::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1475:343:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (5, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor, at::Tensor, at::Tensor, long int>&&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, long int}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’:
/usr/include/c++/6/tuple:626:248:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor>}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1849:313:   required from here
/usr/include/c++/6/tuple:483:67: error: mismatched argument pack lengths while expanding ‘std::is_constructible<_Elements, _UElements&&>’
       return __and_<is_constructible<_Elements, _UElements&&>...>::value;
                                                                   ^~~~~
/usr/include/c++/6/tuple:484:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’:
/usr/include/c++/6/tuple:626:362:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor>}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1849:313:   required from here
/usr/include/c++/6/tuple:489:65: error: mismatched argument pack lengths while expanding ‘std::is_convertible<_UElements&&, _Elements>’
       return __and_<is_convertible<_UElements&&, _Elements>...>::value;
                                                                 ^~~~~
/usr/include/c++/6/tuple:490:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor>&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’:
/usr/include/c++/6/tuple:662:419:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(const std::tuple<_Args1 ...>&) [with _UElements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1849:313:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (5, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor>&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor>&&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’:
/usr/include/c++/6/tuple:686:422:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(std::tuple<_Args1 ...>&&) [with _UElements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, at::Tensor, at::Tensor>::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:1849:313:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (5, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor, at::Tensor, at::Tensor, at::Tensor>&&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor, at::Tensor}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, double, long int>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, double, long int}]’:
/usr/include/c++/6/tuple:626:248:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, double, long int>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor, at::Tensor, double, long int>}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, double, long int>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:2247:170:   required from here
/usr/include/c++/6/tuple:483:67: error: mismatched argument pack lengths while expanding ‘std::is_constructible<_Elements, _UElements&&>’
       return __and_<is_constructible<_Elements, _UElements&&>...>::value;
                                                                   ^~~~~
/usr/include/c++/6/tuple:484:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, double, long int>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, double, long int}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, double, long int>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, double, long int}]’:
/usr/include/c++/6/tuple:626:362:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, double, long int>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor, at::Tensor, double, long int>}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, double, long int>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (4ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:2247:170:   required from here
/usr/include/c++/6/tuple:489:65: error: mismatched argument pack lengths while expanding ‘std::is_convertible<_UElements&&, _Elements>’
       return __and_<is_convertible<_UElements&&, _Elements>...>::value;
                                                                 ^~~~~
/usr/include/c++/6/tuple:490:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, double, long int>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, double, long int}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor, at::Tensor, double, long int>&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, double, long int}]’:
/usr/include/c++/6/tuple:662:419:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, double, long int>::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(const std::tuple<_Args1 ...>&) [with _UElements = {at::Tensor, at::Tensor, double, long int}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, double, long int>::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:2247:170:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (5, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor, at::Tensor, double, long int>&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, double, long int}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor, at::Tensor, double, long int>&&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, double, long int}]’:
/usr/include/c++/6/tuple:686:422:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, double, long int>::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(std::tuple<_Args1 ...>&&) [with _UElements = {at::Tensor, at::Tensor, double, long int}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, double, long int>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor, at::Tensor, double, long int>::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:2247:170:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (5, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor, at::Tensor, double, long int>&&; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, double, long int}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor&, at::Tensor&, at::Tensor&>}; bool <anonymous> = true; _Elements = {at::Tensor&, at::Tensor&, at::Tensor&}]’:
/usr/include/c++/6/tuple:626:248:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor&, at::Tensor&, at::Tensor&>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (3ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor&, at::Tensor&, at::Tensor&>}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor&, at::Tensor&, at::Tensor&>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (3ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:4128:229:   required from here
/usr/include/c++/6/tuple:483:67: error: mismatched argument pack lengths while expanding ‘std::is_constructible<_Elements, _UElements&&>’
       return __and_<is_constructible<_Elements, _UElements&&>...>::value;
                                                                   ^~~~~
/usr/include/c++/6/tuple:484:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor&, at::Tensor&, at::Tensor&>}; bool <anonymous> = true; _Elements = {at::Tensor&, at::Tensor&, at::Tensor&}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor&, at::Tensor&, at::Tensor&>}; bool <anonymous> = true; _Elements = {at::Tensor&, at::Tensor&, at::Tensor&}]’:
/usr/include/c++/6/tuple:626:362:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor&, at::Tensor&, at::Tensor&>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (3ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor&, at::Tensor&, at::Tensor&>}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor&, at::Tensor&, at::Tensor&>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (3ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:4128:229:   required from here
/usr/include/c++/6/tuple:489:65: error: mismatched argument pack lengths while expanding ‘std::is_convertible<_UElements&&, _Elements>’
       return __and_<is_convertible<_UElements&&, _Elements>...>::value;
                                                                 ^~~~~
/usr/include/c++/6/tuple:490:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_ImplicitlyMoveConvertibleTuple() [with _UElements = {std::tuple<at::Tensor&, at::Tensor&, at::Tensor&>}; bool <anonymous> = true; _Elements = {at::Tensor&, at::Tensor&, at::Tensor&}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor&, at::Tensor&, at::Tensor&>&; bool <anonymous> = true; _Elements = {at::Tensor&, at::Tensor&, at::Tensor&}]’:
/usr/include/c++/6/tuple:662:419:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor&, at::Tensor&, at::Tensor&>::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(const std::tuple<_Args1 ...>&) [with _UElements = {at::Tensor&, at::Tensor&, at::Tensor&}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_ConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_ImplicitlyConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor&, at::Tensor&, at::Tensor&>::_NonNestedTuple<const tuple<_Elements ...>&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:4128:229:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (4, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = const std::tuple<at::Tensor&, at::Tensor&, at::Tensor&>&; bool <anonymous> = true; _Elements = {at::Tensor&, at::Tensor&, at::Tensor&}]’ not a return-statement
     }
 ^
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor&, at::Tensor&, at::Tensor&>&&; bool <anonymous> = true; _Elements = {at::Tensor&, at::Tensor&, at::Tensor&}]’:
/usr/include/c++/6/tuple:686:422:   required by substitution of ‘template<class ... _UElements, class _Dummy, typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor&, at::Tensor&, at::Tensor&>::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(std::tuple<_Args1 ...>&&) [with _UElements = {at::Tensor&, at::Tensor&, at::Tensor&}; _Dummy = void; typename std::enable_if<((std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_MoveConstructibleTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor&, at::Tensor&, at::Tensor&>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && std::_TC<(std::is_same<_Dummy, void>::value && (1ul == 1)), at::Tensor&, at::Tensor&, at::Tensor&>::_NonNestedTuple<tuple<_Elements ...>&&>()), bool>::type <anonymous> = <missing>]’
/home/yehor/Tools/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/include/ATen/Functions.h:4128:229:   required from here
/usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (4, should be 2)
       return  __and_<__not_<is_same<tuple<_Elements...>,
                                                                                                                                                                                                                                                    ^    
/usr/include/c++/6/type_traits:1558:8: note: provided for ‘template<class _From, class _To> struct std::is_convertible’
     struct is_convertible
        ^~~~~~~~~~~~~~
/usr/include/c++/6/tuple:502:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_NonNestedTuple() [with _SrcTuple = std::tuple<at::Tensor&, at::Tensor&, at::Tensor&>&&; bool <anonymous> = true; _Elements = {at::Tensor&, at::Tensor&, at::Tensor&}]’ not a return-statement
     }
 ^
error: command '/usr/bin/nvcc' failed with exit status 1

My tools:

gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
Copyright (C) 2017 Free Software Foundation, Inc.
This is free software; see the source for copying conditions.  There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.


nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2017 NVIDIA Corporation
Built on Fri_Nov__3_21:07:56_CDT_2017
Cuda compilation tools, release 9.1, V9.1.85

ModuleNotFoundError: No module named 'cython_bbox'

I followed all the instructions for installation and then tried this command,

python3 demo.py mot --load_model ../models/all_dla34.pth --conf_thres 0.4

I have done cython_bbox installation using pip3 in the conda environment. But still receiving this error.

make error！

cuda10.2 or cuda9.0，Ubuntu18.04

Follow your installation instructions, but make error。What can I do to fix this

sh make.sh
running build
running build_ext
building '_ext' extension
/home/quh/anaconda3/bin/x86_64-conda_cos6-linux-gnu-cc -Wno-unused-result -Wsign-compare -DNDEBUG -fwrapv -O2 -Wall -Wstrict-prototypes -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -pipe -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -pipe -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /home/quh/anaconda3/include -DNDEBUG -D_FORTIFY_SOURCE=2 -O2 -isystem /home/quh/anaconda3/include -fPIC -DWITH_CUDA -I/home/quh/pythonwork/FairMOT/src/lib/models/networks/DCNv2/src -I/home/quh/anaconda3/envs/people-detection/lib/python3.7/site-packages/torch/include -I/home/quh/anaconda3/envs/people-detection/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/quh/anaconda3/envs/people-detection/lib/python3.7/site-packages/torch/include/TH -I/home/quh/anaconda3/envs/people-detection/lib/python3.7/site-packages/torch/include/THC -I:/usr/local/cuda-10.2:/usr/local/cuda/include -I/home/quh/anaconda3/include/python3.7m -c /home/quh/pythonwork/FairMOT/src/lib/models/networks/DCNv2/src/vision.cpp -o build/temp.linux-x86_64-3.7/home/quh/pythonwork/FairMOT/src/lib/models/networks/DCNv2/src/vision.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_ext -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11
cc1plus: warning: command line option '-Wstrict-prototypes' is valid for C/ObjC but not for C++
/home/quh/anaconda3/bin/x86_64-conda_cos6-linux-gnu-cc -Wno-unused-result -Wsign-compare -DNDEBUG -fwrapv -O2 -Wall -Wstrict-prototypes -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -pipe -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -pipe -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /home/quh/anaconda3/include -DNDEBUG -D_FORTIFY_SOURCE=2 -O2 -isystem /home/quh/anaconda3/include -fPIC -DWITH_CUDA -I/home/quh/pythonwork/FairMOT/src/lib/models/networks/DCNv2/src -I/home/quh/anaconda3/envs/people-detection/lib/python3.7/site-packages/torch/include -I/home/quh/anaconda3/envs/people-detection/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/quh/anaconda3/envs/people-detection/lib/python3.7/site-packages/torch/include/TH -I/home/quh/anaconda3/envs/people-detection/lib/python3.7/site-packages/torch/include/THC -I:/usr/local/cuda-10.2:/usr/local/cuda/include -I/home/quh/anaconda3/include/python3.7m -c /home/quh/pythonwork/FairMOT/src/lib/models/networks/DCNv2/src/cpu/dcn_v2_cpu.cpp -o build/temp.linux-x86_64-3.7/home/quh/pythonwork/FairMOT/src/lib/models/networks/DCNv2/src/cpu/dcn_v2_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_ext -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11
cc1plus: warning: command line option '-Wstrict-prototypes' is valid for C/ObjC but not for C++
In file included from /home/quh/pythonwork/FairMOT/src/lib/models/networks/DCNv2/src/cpu/dcn_v2_cpu.cpp:4:0:
/home/quh/anaconda3/envs/people-detection/lib/python3.7/site-packages/torch/include/ATen/cuda/CUDAContext.h:5:10: fatal error: cuda_runtime_api.h: No such file or directory
#include <cuda_runtime_api.h>
^~~~~~~~~~~~~~~~~~~~
compilation terminated.
error: command '/home/quh/anaconda3/bin/x86_64-conda_cos6-linux-gnu-cc' failed with exit status 1

About Training

Hi, I think this is a nice work.
I have a question, if I only use the MOT17 dataset to continue training the model, can I create a ft_mot17_dla34.sh like ft_mot15_dla34.sh?
At the same time,
cd src
python train.py mot --exp_id ft_mot15_dla34 --gpus 0,1 --batch_size 8 --load_model '../models/all_dla34.pth' --data_cfg '../src/lib/cfg/mot15.json'- -num_epochs 10 --lr 1e-5
cd ..
The content will be changed to:
cd src
python train.py mot --exp_id ft_mot17_dla34 --gpus 0,1 --batch_size 8 --load_model '../models/all_dla34.pth' --data_cfg '../src/lib/cfg/mot17.json'- -num_epochs 10 --lr 1e-5
cd ..

Is my reformation correct? If it is not correct, how will I revise it?
Can you give me some suggestions? Thank you!

How to train the model on Custom dataset?

Hello @ifzhang,
You did an impressive work on re-id.
The results are wonderful.
However, I could not see any option/code/method to train the model on a custom multiple person dataset.
May I know the procedure to train the model on such a custom dataset?
Thanking you in anticipation!

there is no seqinfo.ini in Data2DMOT2015, so gen_labels_15.py is useless

I see it's good track result in intensive monitoring scenario;

Nice work!

Hello there, I am the author of JDE.
The performance, as well as the speed of FairMOT, is very promising! Glad to see JDE is helpful in this work. Can I have you wechat if you do not mind?
Here is mine: 13051902595

Segmentation Fault while running demo

Hi

I am facing the following issue when I try to run the demo on a Ubuntu machine with GPU on it.
(FairMOT) @ubuntu:~/ML/FairMOT/src$ python demo.py mot --load_model /home/ML/FairMOT/models/all_dla34.pth --conf_thres 0.4

Fix size testing.
training chunk_sizes: [6, 6]
The output will be saved to /home/ML/FairMOT/src/lib/../../exp/mot/default
heads {'hm': 1, 'wh': 2, 'id': 512, 'reg': 2}
2020-04-16 10:58:12 [INFO]: Starting tracking...
Lenth of the video: 1500 frames
Creating model...
loaded /home/ML/FairMOT/models/all_dla34.pth, epoch 10
2020-04-16 10:58:16 [INFO]: Processing frame 0 (100000.00 fps)
Fatal Python error: Segmentation fault

Current thread 0x00007f53c3767740 (most recent call first):
return self
File "/home/ML/FairMOT/src/lib/models/networks/DCNv2/dcn_v2.py", line 31 in forward
File "/home/ML/FairMOT/src/lib/models/networks/DCNv2/dcn_v2.py", line 128 in forward
File "/home/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547 in call
File "/home/ML/FairMOT/src/lib/models/networks/pose_dla_dcn.py", line 355 in forward
File "/home/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547 in call
File "/home/ML/FairMOT/src/lib/models/networks/pose_dla_dcn.py", line 384 in forward
File "/home/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547 in call
File "/home/ML/FairMOT/src/lib/models/networks/pose_dla_dcn.py", line 411 in forward
File "/home/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547 in call
File "/home/ML/FairMOT/src/lib/models/networks/pose_dla_dcn.py", line 472 in forward
File "/home/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547 in call
File "/home/ML/FairMOT/src/lib/tracker/multitracker.py", line 246 in update
File "/home/ML/FairMOT/src/track.py", line 63 in eval_seq
File "demo.py", line 33 in demo
self.height = img_size[1]
File "demo.py", line 45 in
Segmentation fault (core dumped)

Could you please help with this?
Thanks!
GK

The hrnetv2_w18_imagenet_pretrained.pth

Hello, nice work!

When I used your code. I should download the hrnetv2_w18_imagenet_pretrained.pth. But I found this was very slowly. Could help me with a baiduyunpan about the hrnetv2_w18_imagenet_pretrained.pth. Thank you very much!

how to track other objects

I tried the demo and the results is great.
I wondered can it track other objects,such as cars or bikes, without training??Just use the model you offer?

About the training parameters of hrnet18 baseline model

Hello, thank you for your great job! I see that you have updated a baseline model of hrnet18 that reaches 76.6 on mot15. Is it convenient to provide training parameters, such as the number of iterations and learning rate settings? In addition, if I want to further fine-tune it on mot15, is the learning rate and the number of iterations the same as in the DAL34 fine-tuning script you gave?

No module named 'cython_bbox'

After run python setup.py build develop, It shows:
正在生成代码
已完成代码的生成
running develop
running egg_info
creating DCNv2.egg-info
writing DCNv2.egg-info\PKG-INFO
writing dependency_links to DCNv2.egg-info\dependency_links.txt
writing top-level names to DCNv2.egg-info\top_level.txt
writing manifest file 'DCNv2.egg-info\SOURCES.txt'
reading manifest file 'DCNv2.egg-info\SOURCES.txt'
writing manifest file 'DCNv2.egg-info\SOURCES.txt'
running build_ext
copying build\lib.win-amd64-3.7_ext.cp37-win_amd64.pyd ->
Creating c:\users\dongziqi\anaconda3\envs\fairmot\lib\site-packages\DCNv2.egg-link (link to .)
Adding DCNv2 0.1 to easy-install.pth file

Installed f:\study\fairmot-master\fairmot-master\src\lib\models\networks\dcnv2
Processing dependencies for DCNv2==0.1
Finished processing dependencies for DCNv2==0.1

this is the first build step, I have no idea whether it is success or not.
But it generate _ext.cp37-win_amd64.pyd.
=================================================================And then I run:python demo.py mot --load_model ../models/all_dla34.pth
It shows:
Traceback (most recent call last):
File "demo.py", line 13, in
import datasets.dataset.jde as datasets
File "F:\study\FairMOT-master\FairMOT-master\src\lib\datasets\dataset\jde.py", line 16, in
from cython_bbox import bbox_overlaps as bbox_ious
ModuleNotFoundError: No module named 'cython_bbox'

Then I tried: pip install cython_bbox, However, also failed.
Failed to build cython-bbox
Installing collected packages: cython-bbox
Running setup.py install for cython-bbox ... error

I dont know which step is wrong. Do i failed in the first build step???
Thank you for you answer!!!

How about supporting objects other than People?

I tried it on a Traffic video but I got the same ffmpeg error that I received in my earlier issue #5 so I presume other objects are not yet supported, any plans?

How can I dispaly the confidence of the detected person?

Hi,
Could you tell me how to print the confidence of the detected person? I want to write it to the result.txt file.
Thank you!

On Windows 10 I get ModuleNotFoundError: No module named '_ext'

My lib versions

python 3.6.8
torch==1.4.0
torchsummary==1.5.1
torchvision==0.5.0

I got everything else installed but I get this error on Windows 10 when running demo.py

(pytorch) E:\Documents\Projects\FairMOT\src>python demo.py mot --load_model ../models/hrnetv2_w32_imagenet_pretrained.pth
Traceback (most recent call last):
  File "demo.py", line 14, in <module>
    from track import eval_seq
  File "E:\Documents\Projects\FairMOT\src\track.py", line 15, in <module>
    from tracker.multitracker import JDETracker
  File "E:\Documents\Projects\FairMOT\src\lib\tracker\multitracker.py", line 12, in <module>
    from lib.models.model import create_model, load_model
  File "E:\Documents\Projects\FairMOT\src\lib\models\model.py", line 11, in <module>
    from .networks.pose_dla_dcn import get_pose_net as get_dla_dcn
  File "E:\Documents\Projects\FairMOT\src\lib\models\networks\pose_dla_dcn.py", line 16, in <module>
    from .DCNv2.dcn_v2 import DCN
  File "E:\Documents\Projects\FairMOT\src\lib\models\networks\DCNv2\dcn_v2.py", line 13, in <module>
    import _ext as _backend
ModuleNotFoundError: No module named '_ext'

Though I have the .ext and .lib files copied in the same folder as the script

Also the python setup.py build develop didn't succeed with the attached error
out.txt

which hardware is used during inference?

hi, Greetings! it is good work, i have a question, which hardware is used during inference? thanks

What is the definition of object state?

Hi guys,
I am a learner of FairMOT, and I want to know what is the definition of object state?
Is it the same as the state definition in Sort?
Any answer and idea will be appreciated!

error: command 'C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v10.0\\bin\\nvcc.exe' failed with exit status 2

in the step Dcnv2, run python setup.py build develop;
i meet the error:
error: command 'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.0\bin\nvcc.exe' failed with exit status 2.

python3.7
windows10
anconda
VS2015
cuda10.0

i hope get advice from you !
thank you!

Instructions for running other models

First - great project!
I followed the instructions and it worked (almost) immediately (had some issues because i'm running it on Windows).

Can you provide instructions for running the demo on the other included models? (ctdet_coco_dla_2x / hrnetv2_w18_imagenet_pretrained / hrnetv2_w32_imagenet_pretrained)

I tried using them but received torch warnings/errors. for some of the files I got 0 detections, for the others it simply didn't work

Thanks in advance

Loss is negative？

Hello, I ran the ft_mot20_dla34.sh, and got following log:

2020-04-15-15-52: epoch: 1 |loss 8.929329 | hm_loss 0.650758 | wh_loss 0.932686 | off_loss 0.215589 | id_loss 5.410082 | time 38.966667 | 
2020-04-15-16-31: epoch: 2 |loss 4.626980 | hm_loss 0.527663 | wh_loss 0.815603 | off_loss 0.208662 | id_loss 2.909954 | time 38.533333 | 
2020-04-15-17-09: epoch: 3 |loss 2.803859 | hm_loss 0.488239 | wh_loss 0.790705 | off_loss 0.205520 | id_loss 1.759640 | time 38.516667 | 
2020-04-15-17-48: epoch: 4 |loss 1.848163 | hm_loss 0.462011 | wh_loss 0.775284 | off_loss 0.204124 | id_loss 1.153706 | time 38.516667 | 
2020-04-15-18-27: epoch: 5 |loss 1.303856 | hm_loss 0.443506 | wh_loss 0.763248 | off_loss 0.202581 | id_loss 0.820189 | time 38.566667 | 
2020-04-15-19-05: epoch: 6 |loss 0.945925 | hm_loss 0.425916 | wh_loss 0.745333 | off_loss 0.201435 | id_loss 0.612418 | time 38.683333 | 
2020-04-15-19-44: epoch: 7 |loss 0.714345 | hm_loss 0.414678 | wh_loss 0.742630 | off_loss 0.200537 | id_loss 0.482441 | time 38.816667 | 
2020-04-15-20-23: epoch: 8 |loss 0.536990 | hm_loss 0.403566 | wh_loss 0.732034 | off_loss 0.199769 | id_loss 0.390953 | time 38.716667 | 
2020-04-15-21-02: epoch: 9 |loss 0.394856 | hm_loss 0.394498 | wh_loss 0.727754 | off_loss 0.199561 | id_loss 0.323789 | time 38.700000 | 
2020-04-15-21-40: epoch: 10 |loss 0.266375 | hm_loss 0.385873 | wh_loss 0.718381 | off_loss 0.198318 | id_loss 0.271420 | time 38.750000 | 
2020-04-15-22-19: epoch: 11 |loss 0.160874 | hm_loss 0.380030 | wh_loss 0.719103 | off_loss 0.197896 | id_loss 0.233149 | time 38.733333 | 
2020-04-15-22-58: epoch: 12 |loss 0.060106 | hm_loss 0.373991 | wh_loss 0.711818 | off_loss 0.197058 | id_loss 0.199241 | time 38.733333 | 
2020-04-15-23-37: epoch: 13 |loss -0.018475 | hm_loss 0.369472 | wh_loss 0.711355 | off_loss 0.197177 | id_loss 0.176589 | time 38.733333 | 
2020-04-16-00-15: epoch: 14 |loss -0.094603 | hm_loss 0.365172 | wh_loss 0.702102 | off_loss 0.196040 | id_loss 0.155684 | time 38.733333 | 
2020-04-16-00-54: epoch: 15 |loss -0.153388 | hm_loss 0.363450 | wh_loss 0.704547 | off_loss 0.196285 | id_loss 0.140758 | time 38.766667 | 
2020-04-16-01-33: epoch: 16 |loss -0.230269 | hm_loss 0.356688 | wh_loss 0.691093 | off_loss 0.195501 | id_loss 0.116214 | time 38.766667 | 
2020-04-16-02-12: epoch: 17 |loss -0.236539 | hm_loss 0.356235 | wh_loss 0.694913 | off_loss 0.195542 | id_loss 0.114774 | time 38.800000 | 
2020-04-16-02-51: epoch: 18 |loss -0.246128 | hm_loss 0.355469 | wh_loss 0.692207 | off_loss 0.195600 | id_loss 0.112248 | time 38.783333 | 
2020-04-16-03-30: epoch: 19 |loss -0.255631 | hm_loss 0.354308 | wh_loss 0.689188 | off_loss 0.195229 | id_loss 0.110086 | time 38.833333 | 
2020-04-16-04-08: epoch: 20 |loss -0.264329 | hm_loss 0.353399 | wh_loss 0.686179 | off_loss 0.194963 | id_loss 0.108142 | time 38.850000 | 

As we can see, the loss is negative after the 13th epoch. Is it normal? And is the 12th model is the best according the log?

Undefined name 'dla' in models/networks/dlav0.py

https://github.com/ifzhang/FairMOT/blob/master/src/lib/models/networks/dlav0.py#L417

flake8 testing of https://github.com/ifzhang/FairMOT on Python 3.8.1

$ flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics

./src/lib/models/networks/dlav0.py:417:5: F821 undefined name 'dla'
    dla.BatchNorm = bn
    ^
1     F821 undefined name 'dla'
1

https://flake8.pycqa.org/en/latest/user/error-codes.html

On the flake8 test selection, this PR does not focus on "style violations" (the majority of flake8 error codes that psf/black can autocorrect). Instead these tests are focus on runtime safety and correctness:

• E9 tests are about Python syntax errors usually raised because flake8 can not build an Abstract Syntax Tree (AST). Often these issues are a sign of unused code or code that has not been ported to Python 3. These would be compile-time errors in a compiled language but in a dynamic language like Python they result in the script halting/crashing on the user.
• F63 tests are usually about the confusion between identity and equality in Python. Use ==/!= to compare str, bytes, and int literals is the classic case. These are areas where a == b is True but a is b is False (or vice versa). Python >= 3.8 will raise SyntaxWarnings on these instances.
• F7 tests logic errors and syntax errors in type hints
• F82 tests are almost always undefined names which are usually a sign of a typo, missing imports, or code that has not been ported to Python 3. These also would be compile-time errors in a compiled language but in Python a NameError is raised which will halt/crash the script on the user.

ffmpeg Error

When I try to run the demo.py using the following command:
python demo.py mot --load_model ../models/all_dla34.pth --conf_thres 0.4
I get the following error, when I traced it I found out it is an error related to ffmpeg. Anyone experienced or fixed this error?

[image2 @ 0000024a478eba00] Could find no file with path '../results\frame/%05d.jpg' and index in the range 0-4
../results\frame/%05d.jpg: No such file or directory

I have installed miniconda, cython-bbox, CUDA and other requirements as suggested by the readme and fixed their relative errors I encountered.

Also thank you for your work 👍

CVPR？

Custom detector & Pedestrian dataset

Nice works !
I trained succesfully with almost datasets. Now I have intention to train from multiple datasets to create baseline model, but I have some issues when downloaded Caltech Pedestrian & City Person dataset
I followed instruction at: https://github.com/Zhongdao/Towards-Realtime-MOT/blob/master/DATASET_ZOO.md.
With Caltech Pedestrian dataset, I downloaded all *.tar file from but I don't know how to convert *.seq file to sequence of .png file (or .jpg)
With City Person dataset, I downloaded from Gdrive link but it seems Citypersons.z03 file is not final part zip

Could you pls share link download Cityperson & Caltech_pedestrian dataset (have images & label_with_ids)

One more question, do your code support change custom detector instead of CenterNet detector ?

Thank you so much !

visualization codes bug

FairMOT/src/lib/datasets/dataset/jde.py

Line 209 in 6a84666

plt.plot(labels[:, [1, 3, 3, 1, 1]].T, labels[:, [2, 2, 4, 4, 2]].T, '.-')

Thanks for the great project! It seems that the above line does not fit current codes. It will plot well with:

plt.plot(labels[:, [2, 4, 4, 2, 2]].T, labels[:, [3, 3, 5, 5, 3]].T, '.-')

Can't download baseline model HRNetV2_W18 from Google link

The google link: https://drive.google.com/open?id=1Hna9jmA1jac42u8e9v6HXSS5aldV41YY
Says you need permission to download.

Fixed a spelling mistake

i fixed a spelling mistake in line 41 in src/lib/models/networks/DCNv2/setup.py
https://github.com/BrainlessDylan/FairMOT

i didnt know how to make a pr, sorry lol

Make a custom data set

Please consult the author. In the public mot dataset , "conf: this bbox contains the confidence degree of the object. It can be seen that it is not 0-1 in the traditional sense, and the higher the score is, the higher the confidence degree is."Or how do you make a custom data set? For example ,I want to track the car, How can I make the training datasets，how can I get the "conf "? thanks.

when i try to train mot20, it has a error

File "train.py", line 99, in
main(opt)
File "train.py", line 70, in main
log_dict_train, _ = trainer.train(epoch, train_loader)
File "FairMOT/src/lib/trains/base_trainer.py", line 118, in train
return self.run_epoch('train', epoch, data_loader)
File "FairMOT/src/lib/trains/base_trainer.py", line 61, in run_epoch
for iter_id, batch in enumerate(data_loader):
File "/usr/local/app/anaconda3/envs/tracking/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 801, in next
return self._process_data(data)
File "/usr/local/app/anaconda3/envs/tracking/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 846, in _process_data
data.reraise()
File "/usr/local/app/anaconda3/envs/tracking/lib/python3.7/site-packages/torch/_utils.py", line 369, in reraise
raise self.exc_type(msg)
IndexError: Caught IndexError in DataLoader worker process 6.
Original Traceback (most recent call last):
File "/usr/local/app/anaconda3/envs/tracking/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/usr/local/app/anaconda3/envs/tracking/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/usr/local/app/anaconda3/envs/tracking/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "FairMOT/src/lib/datasets/dataset/jde.py", line 460, in getitem
wh[k] = 1. * w, 1. * h
IndexError: index 400 is out of bounds for axis 0 with size 400

can you help me ?