CRF-RNN for Semantic Image Segmentation - PyTorch version

Live demo: http://crfasrnn.torr.vision
Caffe version: http://github.com/torrvision/crfasrnn
Tensorflow/Keras version: http://github.com/sadeepj/crfasrnn_keras

This repository contains the official PyTorch implementation of the "CRF-RNN" semantic image segmentation method, published in the ICCV 2015 paper Conditional Random Fields as Recurrent Neural Networks. The online demo of this project won the Best Demo Prize at ICCV 2015. Results of this PyTorch code are identical to that of the Caffe and Tensorflow/Keras based versions above.

If you use this code/model for your research, please cite the following paper:

@inproceedings{crfasrnn_ICCV2015,
    author = {Shuai Zheng and Sadeep Jayasumana and Bernardino Romera-Paredes and Vibhav Vineet and
    Zhizhong Su and Dalong Du and Chang Huang and Philip H. S. Torr},
    title  = {Conditional Random Fields as Recurrent Neural Networks},
    booktitle = {International Conference on Computer Vision (ICCV)},
    year   = {2015}
}

Installation Guide

Note: If you are using a Python virtualenv, make sure it is activated before running each command in this guide.

Step 1: Clone the repository

$ git clone https://github.com/sadeepj/crfasrnn_pytorch.git

The root directory of the clone will be referred to as crfasrnn_pytorch hereafter.

Step 2: Install dependencies

Use the requirements.txt file in this repository to install all the dependencies via pip:

$ cd crfasrnn_pytorch
$ pip install -r requirements.txt

After installing the dependencies, run the following commands to make sure they are properly installed:

$ python
>>> import torch

You should not see any errors while importing torch above.

Step 3: Build CRF-RNN custom op

Run setup.py inside the crfasrnn_pytorch/crfasrnn directory:

$ cd crfasrnn_pytorch/crfasrnn
$ python setup.py install

Note that the python command in the console should refer to the Python interpreter associated with your PyTorch installation.

Step 4: Download the pre-trained model weights

Download the model weights from here and place it in the crfasrnn_pytorch directory with the file name crfasrnn_weights.pth.

Step 5: Run the demo

$ cd crfasrnn_pytorch
$ python run_demo.py

If all goes well, you will see the segmentation results in a file named "labels.png".

Contributors

Sadeep Jayasumana (sadeepj)
Harsha Ranasinghe (HarshaPrabhath)

Hello @sadeepj

I am encountering a problem to compile the C++ code parts on windows 10. While it works fine on Linux, wether it be with the newest torch versions or older ones, I am unable to make it work on windows 10 and am encoutnering the following error at compilation

running install
running bdist_egg
running egg_info
writing permuto_cpp.egg-info\PKG-INFO
writing dependency_links to permuto_cpp.egg-info\dependency_links.txt
writing top-level names to permuto_cpp.egg-info\top_level.txt
reading manifest file 'permuto_cpp.egg-info\SOURCES.txt'
writing manifest file 'permuto_cpp.egg-info\SOURCES.txt'
installing library code to build\bdist.win-amd64\egg
running install_lib
running build_ext
C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\utils\cpp_extension.py:274: UserWarning: Error checking compiler version for cl: 'utf-8' codec can't decode byte 0xa2 in position 24: invalid start byte
  warnings.warn('Error checking compiler version for {}: {}'.format(compiler, error))
building 'permuto_cpp' extension
Emitting ninja build file C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\build\temp.win-amd64-3.7\Release\build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[1/1] cl /showIncludes /nologo /Ox /W3 /GL /DNDEBUG /MD /MD /wd4819 /wd4251 /wd4244 /wd4267 /wd4275 /wd4018 /wd4190 /EHsc -IC:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\include -IC:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\include\torch\csrc\api\include -IC:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\include\TH -IC:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\include\THC -IC:\Users\group\anaconda3\envs\crfrnn\include -IC:\Users\group\anaconda3\envs\crfrnn\include "-IC:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\ATLMFC\include" "-IC:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\shared" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\um" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\winrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\cppwinrt" -c C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp /FoC:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\build\temp.win-amd64-3.7\Release\permutohedral.obj -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=permuto_cpp -D_GLIBCXX_USE_CXX11_ABI=0 /std:c++14
FAILED: C:/Users/group/Downloads/test_compil/crfasrnn_pytorch/crfasrnn/build/temp.win-amd64-3.7/Release/permutohedral.obj
cl /showIncludes /nologo /Ox /W3 /GL /DNDEBUG /MD /MD /wd4819 /wd4251 /wd4244 /wd4267 /wd4275 /wd4018 /wd4190 /EHsc -IC:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\include -IC:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\include\torch\csrc\api\include -IC:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\include\TH -IC:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\include\THC -IC:\Users\group\anaconda3\envs\crfrnn\include -IC:\Users\group\anaconda3\envs\crfrnn\include "-IC:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\ATLMFC\include" "-IC:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\shared" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\um" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\winrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\cppwinrt" -c C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp /FoC:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\build\temp.win-amd64-3.7\Release\permutohedral.obj -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=permuto_cpp -D_GLIBCXX_USE_CXX11_ABI=0 /std:c++14
Nota: inclusión del archivo: C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.h
Nota: inclusión del archivo:  C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\cstdlib
Nota: inclusión del archivo:   C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\yvals_core.h
Nota: inclusión del archivo:    C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\vcruntime.h
Nota: inclusión del archivo:     C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\sal.h
Nota: inclusión del archivo:      C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\concurrencysal.h
Nota: inclusión del archivo:     C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\vadefs.h
Nota: inclusión del archivo:    C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\xkeycheck.h
Nota: inclusión del archivo:   C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\math.h
Nota: inclusión del archivo:    C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_math.h
Nota: inclusión del archivo:     C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt.h
Nota: inclusión del archivo:   C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\stdlib.h
Nota: inclusión del archivo:    C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_malloc.h
Nota: inclusión del archivo:    C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_search.h
Nota: inclusión del archivo:     C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\stddef.h
Nota: inclusión del archivo:    C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_wstdlib.h
Nota: inclusión del archivo:    C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\limits.h
Nota: inclusión del archivo:  C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\vector
Nota: inclusión del archivo:   C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\xmemory
Nota: inclusión del archivo:    C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\cstdint
Nota: inclusión del archivo:     C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\stdint.h
Nota: inclusión del archivo:    C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\limits
Nota: inclusión del archivo:     C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\cfloat
Nota: inclusión del archivo:      C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\float.h
Nota: inclusión del archivo:     C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\climits
Nota: inclusión del archivo:     C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\cwchar
Nota: inclusión del archivo:      C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\cstdio
Nota: inclusión del archivo:       C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\stdio.h
Nota: inclusión del archivo:        C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_wstdio.h
Nota: inclusión del archivo:         C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_stdio_config.h
Nota: inclusión del archivo:      C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\wchar.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_memcpy_s.h
Nota: inclusión del archivo:        C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\errno.h
Nota: inclusión del archivo:        C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\vcruntime_string.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_wconio.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_wctype.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_wdirect.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_wio.h
Nota: inclusión del archivo:        C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_share.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_wprocess.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_wstring.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_wtime.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\sys/stat.h
Nota: inclusión del archivo:        C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\sys/types.h
Nota: inclusión del archivo:     C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\intrin0.h
Nota: inclusión del archivo:      C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\intrin0.inl.h
Nota: inclusión del archivo:     C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\isa_availability.h
Nota: inclusión del archivo:     C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\xstddef
Nota: inclusión del archivo:      C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\cstddef
Nota: inclusión del archivo:       C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\xtr1common
Nota: inclusión del archivo:      C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\initializer_list
Nota: inclusión del archivo:    C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\new
Nota: inclusión del archivo:     C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\exception
Nota: inclusión del archivo:      C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\yvals.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\crtdbg.h
Nota: inclusión del archivo:        C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\vcruntime_new_debug.h
Nota: inclusión del archivo:         C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\vcruntime_new.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\crtdefs.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\use_ansi.h
Nota: inclusión del archivo:      C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\type_traits
Nota: inclusión del archivo:      C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\malloc.h
Nota: inclusión del archivo:      C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\vcruntime_exception.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\eh.h
Nota: inclusión del archivo:        C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_terminate.hNota: inclusión del archivo:    C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\xatomic.h
Nota: inclusión del archivo:    C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\xutility
Nota: inclusión del archivo:     C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\cstring
Nota: inclusión del archivo:      C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\string.h
Nota: inclusión del archivo:       C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\corecrt_memory.h
Nota: inclusión del archivo:     C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\utility
Nota: inclusión del archivo:  C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\cassert
Nota: inclusión del archivo:   C:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt\assert.h
Nota: inclusión del archivo:  C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\cmath
C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp(327): error C2065: 'HashTableCopy': identificador no declarado
C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp(327): error C2146: error de sintaxis: falta ';' delante del identificador 'hash_table'
C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp(327): error C3861: 'hash_table': no se encontró el identificador
C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp(360): error C2065: 'assert': identificador no declarado
C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp(360): error C2143: error de sintaxis: falta ';' delante de 'constante'
C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp(360): error C2014: el comando de preprocesador debe empezar con un primer espacio que no esté en blanco
C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp(361): error C2065: 'feature': identificador no declarado
C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp(432): error C2065: 'hash_table': identificador no declarado
C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp(449): error C2065: 'hash_table': identificador no declarado
C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp(460): error C2065: 'hash_table': identificador no declarado
C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp(468): error C2065: 'hash_table': identificador no declarado
C:\Users\group\Downloads\test_compil\crfasrnn_pytorch\crfasrnn\permutohedral.cpp(469): error C2065: 'hash_table': identificador no declarado
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\utils\cpp_extension.py", line 1517, in _run_ninja_build
    subprocess.run(
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\subprocess.py", line 512, in run
    output=stdout, stderr=stderr)
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "setup.py", line 6, in <module>
    cmdclass={'build_ext': cpp_extension.BuildExtension})
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\setuptools\__init__.py", line 153, in setup
    return distutils.core.setup(**attrs)
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\core.py", line 148, in setup
    dist.run_commands()
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\dist.py", line 966, in run_commands
    self.run_command(cmd)
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\dist.py", line 985, in run_command
    cmd_obj.run()
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\setuptools\command\install.py", line 67, in run
    self.do_egg_install()
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\setuptools\command\install.py", line 109, in do_egg_install
    self.run_command('bdist_egg')
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\cmd.py", line 313, in run_command
    self.distribution.run_command(command)
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\dist.py", line 985, in run_command
    cmd_obj.run()
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\setuptools\command\bdist_egg.py", line 164, in run
    cmd = self.call_command('install_lib', warn_dir=0)
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\setuptools\command\bdist_egg.py", line 150, in call_command
    self.run_command(cmdname)
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\cmd.py", line 313, in run_command
    self.distribution.run_command(command)
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\dist.py", line 985, in run_command
    cmd_obj.run()
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\setuptools\command\install_lib.py", line 11, in run
    self.build()
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\command\install_lib.py", line 107, in build
    self.run_command('build_ext')
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\cmd.py", line 313, in run_command
    self.distribution.run_command(command)
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\dist.py", line 985, in run_command
    cmd_obj.run()
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\setuptools\command\build_ext.py", line 79, in run
    _build_ext.run(self)
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\command\build_ext.py", line 340, in run
    self.build_extensions()
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\utils\cpp_extension.py", line 653, in build_extensions
    build_ext.build_extensions(self)
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\command\build_ext.py", line 449, in build_extensions
    self._build_extensions_serial()
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\command\build_ext.py", line 474, in _build_extensions_serial
    self.build_extension(ext)
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\setuptools\command\build_ext.py", line 202, in build_extension
    _build_ext.build_extension(self, ext)
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\distutils\command\build_ext.py", line 534, in build_extension
    depends=ext.depends)
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\utils\cpp_extension.py", line 635, in win_wrap_ninja_compile
    with_cuda=with_cuda)
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\utils\cpp_extension.py", line 1238, in _write_ninja_file_and_compile_objects
    error_prefix='Error compiling objects for extension')
  File "C:\Users\group\anaconda3\envs\crfrnn\lib\site-packages\torch\utils\cpp_extension.py", line 1517, in _run_ninja_build
    subprocess.run(
RuntimeError: Error compiling objects for extension

I would be glad if you had some ideas to deal with this problem

Thanks in advance

Error compiling on windows 10

opened by QuanticDisaster 2

Installation Problems

When executing python setup.py install I get an error which says that a newer version of GCC is needed. The warning references to this issue. However the suggested approaches from the issue did not work for me. I am using conda and don't have sudo rights.

Finally, I resolved the error by running: conda install -c anaconda gxx_linux-64 I hope this helps anyone who has the same problem.

opened by RadekZenkl 3
FCN pretrained weights on COCO data

I am looking for a pre-trained FCN model on COCO data. I noticed in your article that FCN is trained on COCO data. Could you provide weights? Thank you very much!

opened by HWLMX 0
UNet version

I'm testing to see the benefits of having the crf layer with a unet. Currently the model returns a loss that oscillates between 3&4 with the crf, while the unet (from the original paper) converges to a loss of .021. Any advice?

opened by mavaylon1 2
Training on other backbone and datasets

Hello, I want to ask that if these pytorch crfasrnn model can be used for training? I want to train a model with other backbone instead of FCN. By the way, if I want to train on pascal_context dataset, after I change the label number to 59, and reinstall setup.py install, then it might should work smoothly? Thanks you !

opened by pp00704831 4

CRF-RNN for Semantic Image Segmentation - PyTorch version

Related tags

Overview

CRF-RNN for Semantic Image Segmentation - PyTorch version

Installation Guide

Step 1: Clone the repository

Step 2: Install dependencies

Step 3: Build CRF-RNN custom op

Step 4: Download the pre-trained model weights

Step 5: Run the demo

Contributors

Comments

Error compiling on windows 10

Installation Problems

FCN pretrained weights on COCO data

UNet version

Training on other backbone and datasets

Releases(0.0.1)

0.0.1(Nov 30, 2019)

Owner

Sadeep Jayasumana

Implementation of gaze tracking and demo

Differentiable Simulation of Soft Multi-body Systems

Code for the Image similarity challenge.

A universal memory dumper using Frida

TLDR: Twin Learning for Dimensionality Reduction

This repository contains code for the paper "Disentangling Label Distribution for Long-tailed Visual Recognition", published at CVPR' 2021

Deep Learning Emotion decoding using EEG data from Autism individuals

Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset (CVPR'19)

This is the code for the paper "Motion-Focused Contrastive Learning of Video Representations" (ICCV'21).

Make your master artistic punk avatar through machine learning world famous paintings.

Consensus score for tripadvisor

A Keras implementation of YOLOv3 (Tensorflow backend)

WaveFake: A Data Set to Facilitate Audio DeepFake Detection

Certifiable Outlier-Robust Geometric Perception

Unadversarial Examples: Designing Objects for Robust Vision

The undersampled DWI image using Slice-Interleaved Diffusion Encoding (SIDE) method can be reconstructed by the UNet network.

Automated Evidence Collection for Fake News Detection

An efficient implementation of GPNN

This repository contains the code needed to train Mega-NeRF models and generate the sparse voxel octrees

A tutorial showing how to train, convert, and run TensorFlow Lite object detection models on Android devices, the Raspberry Pi, and more!