Dockerコンテナ内のCUDAのPATHについて

Question

前提・実現したいこと

dockerコンテナ内でubuntu16.04のイメージを獲得し，
python3.6.7で環境構築している際に，cuda9.0を入れてみたところパスが通っていないとエラーが出ました．
エラーは対象のlib内でmakeコマンドを入力した際に，別のエラーで，setup_linux.pyを実行しろとのことだったので，実行した結果今回のエラーが出ました．

発生している問題・エラーメッセージ

OSError: The nvcc binary could not be located in your $PATH. Either add it to your path, or set $CUDAHOME

該当のソースコード

import os
from os.path import join as pjoin
from setuptools import setup
from distutils.extension import Extension
from Cython.Distutils import build_ext
import numpy as np


def find_in_path(name, path):
    "Find a file in a search path"
    # Adapted fom
    # http://code.activestate.com/recipes/52224-find-a-file-given-a-search-path/
    for dir in path.split(os.pathsep):
        binpath = pjoin(dir, name)
        if os.path.exists(binpath):
            return os.path.abspath(binpath)
    return None


def locate_cuda():
    """Locate the CUDA environment on the system
    Returns a dict with keys 'home', 'nvcc', 'include', and 'lib64'
    and values giving the absolute path to each directory.
    Starts by looking for the CUDAHOME env variable. If not found, everything
    is based on finding 'nvcc' in the PATH.
    """
    # first check if the CUDAHOME env variable is in use
    if 'CUDAHOME' in os.environ:
        home = os.environÆ'CUDAHOME'Å
        nvcc = pjoin(home, 'bin', 'nvcc')
    else:
        # otherwise, search the PATH for NVCC
        default_path = pjoin(os.sep, 'usr', 'local', 'cuda', 'bin')
        nvcc = find_in_path('nvcc', os.environÆ'PATH'Å + os.pathsep + default_path)
        if nvcc is None:
            raise EnvironmentError('The nvcc binary could not be '
                'located in your $PATH. Either add it to your path, or set $CUDAHOME')
        home = os.path.dirname(os.path.dirname(nvcc))

    cudaconfig = æ'home':home, 'nvcc':nvcc,
                  'include': pjoin(home, 'include'),
                  'lib64': pjoin(home, 'lib64')å
    for k, v in cudaconfig.items():
        if not os.path.exists(v):
            raise EnvironmentError('The CUDA %s path could not be located in %s' % (k, v))

    return cudaconfig
CUDA = locate_cuda()


# Obtain the numpy include directory.  This logic works across numpy versions.
try:
    numpy_include = np.get_include()
except AttributeError:
    numpy_include = np.get_numpy_include()


def customize_compiler_for_nvcc(self):
    """inject deep into distutils to customize how the dispatch
    to gcc/nvcc works.
    If you subclass UnixCCompiler, it's not trivial to get your subclass
    injected in, and still have the right customizations (i.e.
    distutils.sysconfig.customize_compiler) run on it. So instead of going
    the OO route, I have this. Note, it's kindof like a wierd functional
    subclassing going on."""

    # tell the compiler it can processes .cu
    self.src_extensions.append('.cu')

    # save references to the default compiler_so and _comple methods
    default_compiler_so = self.compiler_so
    super = self._compile

    # now redefine the _compile method. This gets executed for each
    # object but distutils doesn't have the ability to change compilers
    # based on source extension: we add it.
    def _compile(obj, src, ext, cc_args, extra_postargs, pp_opts):
        if os.path.splitext(src)Æ1Å == '.cu':
            # use the cuda for .cu files
            self.set_executable('compiler_so', CUDAÆ'nvcc'Å)
            # use only a subset of the extra_postargs, which are 1-1 translated
            # from the extra_compile_args in the Extension class
            postargs = extra_postargsÆ'nvcc'Å
        else:
            postargs = extra_postargsÆ'gcc'Å

        super(obj, src, ext, cc_args, postargs, pp_opts)
        # reset the default compiler_so, which we might have changed for cuda
        self.compiler_so = default_compiler_so

    # inject our redefined _compile method into the class
    self._compile = _compile


# run the customize_compiler
class custom_build_ext(build_ext):
    def build_extensions(self):
        customize_compiler_for_nvcc(self.compiler)
        build_ext.build_extensions(self)


ext_modules = Æ
    Extension(
        "cpu_nms",
        Æ"cpu_nms.pyx"Å,
        extra_compile_args=æ'gcc': Æ"-Wno-cpp", "-Wno-unused-function"Åå,
        include_dirs = Ænumpy_includeÅ
    ),
    Extension('gpu_nms',
        Æ'nms_kernel.cu', 'gpu_nms.pyx'Å,
        library_dirs=ÆCUDAÆ'lib64'ÅÅ,
        libraries=Æ'cudart'Å,
        language='c++',
        runtime_library_dirs=ÆCUDAÆ'lib64'ÅÅ,
        # this syntax is specific to this build system
        # we're only going to use certain compiler args with nvcc and not with
        # gcc the implementation of this trick is in customize_compiler() below
        extra_compile_args=æ'gcc': Æ"-Wno-unused-function"Å,
                            'nvcc': Æ'-arch=sm_35',
                                     '--ptxas-options=-v',
                                     '-c',
                                     '--compiler-options',
                                     "'-fPIC'"Åå,
        include_dirs = Ænumpy_include, CUDAÆ'include'ÅÅ
    ),
Å

setup(
    name='nms',
    ext_modules=ext_modules,
    # inject our custom trigger
    cmdclass=æ'build_ext': custom_build_extå,
)

試したこと

調べて，/.bashrcにパスを追加する以下のコマンドを入力しました．

export CUDA_HOME=/usr/local/cuda
export LD_LIBRARY_PATH=${CUDA_HOME}/lib64

PATH=${CUDA_HOME}/bin:${PATH}
export PATH

しかし，入力しても同じエラーが出ます．

補足情報（FW/ツールのバージョンなど）

ubuntu16.04
python3.6.7
torch 1.5.0