House3D: A Rich and Realistic 3D Environment

Related tags

Deep LearningHouse3D
Overview

House3D: A Rich and Realistic 3D Environment

Yi Wu, Yuxin Wu, Georgia Gkioxari and Yuandong Tian

House3D is a virtual 3D environment which consists of thousands of indoor scenes equipped with a diverse set of scene types, layouts and objects sourced from the SUNCG dataset. It consists of over 45k indoor 3D scenes, ranging from studios to two-storied houses with swimming pools and fitness rooms. All 3D objects are fully annotated with category labels. Agents in the environment have access to observations of multiple modalities, including RGB images, depth, segmentation masks and top-down 2D map views. The renderer runs at thousands frames per second, making it suitable for large-scale RL training.

Usage instructions can be found at INSTRUCTION.md

Existing Research Projects with House3D

A. RoomNav (paper)

Yi Wu, Yuxin Wu, Georgia Gkioxari, Yuandong Tian

In this work we introduce a concept learning task, RoomNav, where an agent is asked to navigate to a destination specified by a high-level concept, e.g. dining room. We demonstrated two neural models: a gated-CNN and a gated-LSTM, which effectively improve the agent's sensitivity to different concepts. For evaluation, we emphasize on generalization ability and show that our agent can generalize across environments due to the diverse and large-scale dataset.

B. Embodied QA (project page | EQA paper | NMC paper)

Abhishek Das, Samyak Datta, Georgia Gkioxari, Stefan Lee, Devi Parikh, Dhruv Batra

Embodied Question Answering is a new AI task where an agent is spawned at a random location in a 3D environment and asked a natural language question ("What color is the car?"). In order to answer, the agent must first intelligently navigate to explore the environment, gather information through first-person (egocentric) vision, and then answer the question ("orange").

Citation

If you use our platform in your research, you can cite us with:

@article{wu2018building,
  title={Building generalizable agents with a realistic and rich 3D environment},
  author={Wu, Yi and Wu, Yuxin and Gkioxari, Georgia and Tian, Yuandong},
  journal={arXiv preprint arXiv:1801.02209},
  year={2018}
}

License

House3D is released under the Apache 2.0 license.

Comments
  • Error occurred when compile to build objrender

    Error occurred when compile to build objrender

    when I runing SYSTEM=conda.linux PYTHON_CONFIG=/home/zjw/anaconda3/envs/LG/bin/python-config make -j It comes that: /usr/include/glm/detail/type_vec3.inl:86:33: error: invalid static_cast from type ‘const glm::detail::tvec3<float, (glm::precision)0u>’ to type ‘float’ /usr/include/glm/detail/type_vec3.inl:86:33: error: invalid static_cast from type ‘const glm::detail::tvec3<float, (glm::precision)0u>’ to type ‘float’

    make: *** [build/objview-suncg.o] Error 1 make: *** [build/suncg/render.o] Error 1

    opened by Zzmonica 43
  • error: ERROR::FRAMEBUFFER: Framebuffer is not complete! ErrorCode=36061

    error: ERROR::FRAMEBUFFER: Framebuffer is not complete! ErrorCode=36061

    I am using the docker to run House3D so I guess there is no build issues. When I run python3 test-rendering.py $TEST_HOUSE or ./renderer/test-rectangle.bin headless the error error: ERROR::FRAMEBUFFER: Framebuffer is not complete! ErrorCode=36061 occur.

    The output of ./debug-build.sh is as follow:

    PATH:
/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin

CPATH:


PKG_CONFIG_PATH:


LIBRARY_PATH:


LD_LIBRARY_PATH:
/usr/lib/x86_64-linux-gnu:/usr/lib/i386-linux-gnu:/usr/local/nvidia/lib:/usr/local/nvidia/lib64

PYTHONPATH:


ldconfig:
	libEGL_nvidia.so.0 (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libEGL_nvidia.so.0
	libEGL_nvidia.so.0 (libc6) => /usr/lib/i386-linux-gnu/libEGL_nvidia.so.0
	libEGL_mesa.so.0 (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libEGL_mesa.so.0
	libEGL_mesa.so.0 (libc6) => /usr/lib/i386-linux-gnu/libEGL_mesa.so.0
	libEGL.so.1 (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libEGL.so.1
	libEGL.so.1 (libc6) => /usr/lib/i386-linux-gnu/libEGL.so.1
	libEGL.so (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libEGL.so
	libEGL.so (libc6) => /usr/lib/i386-linux-gnu/libEGL.so
+ pkg-config --cflags --libs glfw3
-lglfw
+ '[' '!' '' ']'
+ pkg-config --cflags --libs libglvnd

+ pkg-config --cflags --libs egl
-I/usr/include/libdrm -lEGL
+ which find
/usr/bin/find
+ which pkg-config
/usr/bin/pkg-config
+ which python3-config
/usr/bin/python3-config
+ python3-config --includes --ldflags
-I/usr/include/python3.6m -I/usr/include/python3.6m
-L/usr/lib/python3.6/config-3.6m-x86_64-linux-gnu -L/usr/lib -lpython3.6m -lpthread -ldl  -lutil -lm  -Xlinker -export-dynamic -Wl,-O1 -Wl,-Bsymbolic-functions
+ '[' ']'
+ g++ --version
g++ (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0
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.

+ '[' -f ../House3D/objrender.so ']'
+ '[' -f objview.bin ']

    The output of ./test-rectangle.bin egl is :

    [EGL] Detected 1 devices. Using device 0
----------- OpenGL Context Info --------------
GL Version: 4.5.0 NVIDIA 384.130
GLSL Version: 4.50 NVIDIA
Vendor: NVIDIA Corporation
Renderer: GeForce GTX 1060 6GB/PCIe/SSE2

    The output of ./test-rectangle.bin headless is:

    ----------- OpenGL Context Info --------------
GL Version: 3.3.0 NVIDIA 384.130
GLSL Version: 3.30 NVIDIA via Cg compiler
Vendor: NVIDIA Corporation
Renderer: GeForce GTX 1060 6GB/PCIe/SSE2
----------------------------------------------
error: ERROR::FRAMEBUFFER: Framebuffer is not complete! ErrorCode=36061

    Many thanks!

    opened by weihaosky 13
  • Error in running objview-offline.bin

    Error in running objview-offline.bin

    Hi, I am getting the following error when I run objview-offline.bin.

    [EGL] Detected 0 devices. Using device 0 assertion "device < numDevices" failed, in EGLContext, (gl/glContext.cc:137) Aborted (core dumped)

    Here's the output of debug_build.sh

    PATH:
/root/anaconda3/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/u
sr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin

CPATH:


PKG_CONFIG_PATH:


LIBRARY_PATH:
/usr/local/cuda/lib64/stubs:

LD_LIBRARY_PATH:
/root/anaconda3/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64

+ pkg-config --cflags --libs glew
Package glew was not found in the pkg-config search path.
Perhaps you should add the directory containing `glew.pc'
to the PKG_CONFIG_PATH environment variable
No package 'glew' found
+ pkg-config --cflags --libs glfw3
-I/usr/include/libdrm -lglfw
+ '[' '!' '' ']'
+ pkg-config --cflags --libs libglvnd
Package libglvnd was not found in the pkg-config search path.
Perhaps you should add the directory containing `libglvnd.pc'
to the PKG_CONFIG_PATH environment variable
No package 'libglvnd' found
+ pkg-config --cflags --libs egl
-I/usr/include/libdrm -lEGL
+ which find
/usr/bin/find
+ which pkg-config
/usr/bin/pkg-config
+ which python-config
/usr/bin/python-config
+ python-config --includes --ldflags
-I/usr/include/python2.7 -I/usr/include/x86_64-linux-gnu/python2.7
-L/usr/lib/python2.7/config-x86_64-linux-gnu -L/usr/lib -lpython2.7 -lpthread -ldl  -lutil -lm  -Xlinker -export-dynamic -Wl,-O1 -Wl,-Bsymbolic-functions
+ '[' ']'
+ g++ --version
g++ (Ubuntu 5.4.0-6ubuntu1~16.04.6) 5.4.0 20160609
Copyright (C) 2015 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.

+ '[' -f ../House3D/objrender.so ']'
+ ldd ../House3D/objrender.so
        linux-vdso.so.1 =>  (0x00007ffefcbbc000)
        libpng16.so.16 => /root/anaconda3/lib/libpng16.so.16 (0x00007f9c7ea50000)
        libGL.so.1 => /usr/local/nvidia/lib64/libGL.so.1 (0x00007f9c7e7ac000)
        libEGL.so.1 => /usr/local/nvidia/lib64/libEGL.so.1 (0x00007f9c7e59a000)
        libX11.so.6 => /usr/lib/x86_64-linux-gnu/libX11.so.6 (0x00007f9c7e260000)
        libglfw.so.3 => /usr/lib/x86_64-linux-gnu/libglfw.so.3 (0x00007f9c7e04a000)
        libjpeg.so.9 => /root/anaconda3/lib/libjpeg.so.9 (0x00007f9c7de0e000)
        libpython3.6m.so.1.0 => /root/anaconda3/lib/libpython3.6m.so.1.0 (0x00007f9c7d8c9000)
        libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007f9c7d6ac000)
        libstdc++.so.6 => /root/anaconda3/lib/libstdc++.so.6 (0x00007f9c7d372000)
        libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007f9c7d069000)
        libgcc_s.so.1 => /root/anaconda3/lib/libgcc_s.so.1 (0x00007f9c7ce57000)
        libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f9c7ca8d000)
        /lib64/ld-linux-x86-64.so.2 (0x00007f9c7ef87000)
        libz.so.1 => /root/anaconda3/lib/./libz.so.1 (0x00007f9c7c876000)
        libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007f9c7c672000)
        libGLX.so.0 => /usr/local/nvidia/lib64/libGLX.so.0 (0x00007f9c7c442000)
        libGLdispatch.so.0 => /usr/local/nvidia/lib64/libGLdispatch.so.0 (0x00007f9c7c174000)
        libxcb.so.1 => /root/anaconda3/lib/libxcb.so.1 (0x00007f9c7bf4b000)
        librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007f9c7bd43000)
        libXrandr.so.2 => /usr/lib/x86_64-linux-gnu/libXrandr.so.2 (0x00007f9c7bb38000)
        libXinerama.so.1 => /usr/lib/x86_64-linux-gnu/libXinerama.so.1 (0x00007f9c7b935000)
        libXi.so.6 => /usr/lib/x86_64-linux-gnu/libXi.so.6 (0x00007f9c7b725000)
        libXxf86vm.so.1 => /usr/lib/x86_64-linux-gnu/libXxf86vm.so.1 (0x00007f9c7b51f000)
        libXcursor.so.1 => /usr/lib/x86_64-linux-gnu/libXcursor.so.1 (0x00007f9c7b315000)
        libutil.so.1 => /lib/x86_64-linux-gnu/libutil.so.1 (0x00007f9c7b112000)
        libXext.so.6 => /usr/lib/x86_64-linux-gnu/libXext.so.6 (0x00007f9c7af00000)
        libXau.so.6 => /usr/lib/x86_64-linux-gnu/libXau.so.6 (0x00007f9c7acfc000)
        libXrender.so.1 => /usr/lib/x86_64-linux-gnu/libXrender.so.1 (0x00007f9c7aaf2000)
        libXfixes.so.3 => /usr/lib/x86_64-linux-gnu/libXfixes.so.3 (0x00007f9c7a8ec000)

    I am using Anaconda 3 inside a docker on a Ubuntu16 system with 2 Nvidia GPUs.

    opened by devendrachaplot 12
  • Error when running test-rendering.py

    Error when running test-rendering.py

    Error message:

    error: Failed to get function pointer of eglQueryDevicesEXT/eglGetPlatformDisplayEXT! Maybe EGL extensions are unsupported.

    On Ubuntu 14.04. Exactly followed the instructions. glfw3 and glm were installed at /usr/local. Build command

    PYTHON_CONFIG=python3-config make

    Output of debug-build.sh

    PATH:
/home/hzjiang/.nvm/versions/node/v8.9.4/bin:/usr/local/cuda/bin:/usr/local/cuda/bin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/usr/lib/jvm/java-8-oracle/bin:/usr/lib/jvm/java-8-oracle/db/bin:/usr/lib/jvm/java-8-oracle/jre/bin

CPATH:


PKG_CONFIG_PATH:


LIBRARY_PATH:


LD_LIBRARY_PATH:
/usr/local/lib:/usr/local/cuda/lib:/usr/local/cuda/lib64:/usr/local/cuda/lib:/usr/local/cuda/lib64:

+ pkg-config --cflags --libs glew
-I/usr/include/GL -I/usr/include/libdrm  -lGLEW -lGLU -lGL  
+ pkg-config --cflags --libs glfw3
-I/usr/local/include  -L/usr/local/lib -lglfw  
+ [ !  ]
+ pkg-config --cflags --libs libglvnd
Package libglvnd was not found in the pkg-config search path.
Perhaps you should add the directory containing `libglvnd.pc'
to the PKG_CONFIG_PATH environment variable
No package 'libglvnd' found
+ pkg-config --cflags --libs egl
-I/usr/include/libdrm  -lEGL  
+ which find
/usr/bin/find
+ which pkg-config
/usr/bin/pkg-config
+ which python-config
/usr/bin/python-config
+ python-config --includes --ldflags
-I/usr/include/python2.7 -I/usr/include/x86_64-linux-gnu/python2.7
-L/usr/lib/python2.7/config-x86_64-linux-gnu -L/usr/lib -lpthread -ldl  -lutil -lm  -lpython2.7 -Xlinker -export-dynamic -Wl,-O1 -Wl,-Bsymbolic-functions
+ [ ]
+ g++ --version
g++ (Ubuntu 4.9.4-2ubuntu1~14.04.1) 4.9.4
Copyright (C) 2015 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.

+ [ -f ../House3D/objrender.so ]
+ ldd ../House3D/objrender.so
	linux-vdso.so.1 =>  (0x00007ffc26ddb000)
	libGL.so.1 => /usr/lib/x86_64-linux-gnu/mesa/libGL.so.1 (0x00007f5fa1fe4000)
	libEGL.so.1 => /usr/lib/x86_64-linux-gnu/mesa-egl/libEGL.so.1 (0x00007f5fa1dbf000)
	libX11.so.6 => /usr/lib/x86_64-linux-gnu/libX11.so.6 (0x00007f5fa1a8a000)
	libpng16.so.16 => /usr/local/lib/libpng16.so.16 (0x00007f5fa1858000)
	libglfw.so.3 => /usr/local/lib/libglfw.so.3 (0x00007f5fa1635000)
	libjpeg.so.8 => /usr/lib/x86_64-linux-gnu/libjpeg.so.8 (0x00007f5fa13e0000)
	libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007f5fa11c2000)
	libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007f5fa0fbe000)
	libutil.so.1 => /lib/x86_64-linux-gnu/libutil.so.1 (0x00007f5fa0dbb000)
	libstdc++.so.6 => /usr/lib/x86_64-linux-gnu/libstdc++.so.6 (0x00007f5fa0aa8000)
	libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007f5fa07a2000)
	libgcc_s.so.1 => /lib/x86_64-linux-gnu/libgcc_s.so.1 (0x00007f5fa058b000)
	libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f5fa01c2000)
	/lib64/ld-linux-x86-64.so.2 (0x00007f5fa2846000)
	libglapi.so.0 => /usr/lib/x86_64-linux-gnu/libglapi.so.0 (0x00007f5f9ff9b000)
	libXext.so.6 => /usr/lib/x86_64-linux-gnu/libXext.so.6 (0x00007f5f9fd89000)
	libXdamage.so.1 => /usr/lib/x86_64-linux-gnu/libXdamage.so.1 (0x00007f5f9fb86000)
	libXfixes.so.3 => /usr/lib/x86_64-linux-gnu/libXfixes.so.3 (0x00007f5f9f980000)
	libX11-xcb.so.1 => /usr/lib/x86_64-linux-gnu/libX11-xcb.so.1 (0x00007f5f9f77e000)
	libxcb-glx.so.0 => /usr/lib/x86_64-linux-gnu/libxcb-glx.so.0 (0x00007f5f9f567000)
	libxcb-dri2.so.0 => /usr/lib/x86_64-linux-gnu/libxcb-dri2.so.0 (0x00007f5f9f362000)
	libxcb-dri3.so.0 => /usr/lib/x86_64-linux-gnu/libxcb-dri3.so.0 (0x00007f5f9f15f000)
	libxcb-present.so.0 => /usr/lib/x86_64-linux-gnu/libxcb-present.so.0 (0x00007f5f9ef5c000)
	libxcb-sync.so.1 => /usr/lib/x86_64-linux-gnu/libxcb-sync.so.1 (0x00007f5f9ed56000)
	libxcb.so.1 => /usr/lib/x86_64-linux-gnu/libxcb.so.1 (0x00007f5f9eb37000)
	libxshmfence.so.1 => /usr/lib/x86_64-linux-gnu/libxshmfence.so.1 (0x00007f5f9e935000)
	libXxf86vm.so.1 => /usr/lib/x86_64-linux-gnu/libXxf86vm.so.1 (0x00007f5f9e72f000)
	libdrm.so.2 => /usr/lib/x86_64-linux-gnu/libdrm.so.2 (0x00007f5f9e521000)
	libxcb-xfixes.so.0 => /usr/lib/x86_64-linux-gnu/libxcb-xfixes.so.0 (0x00007f5f9e31a000)
	libwayland-client.so.0 => /usr/lib/x86_64-linux-gnu/libwayland-client.so.0 (0x00007f5f9e10d000)
	libwayland-server.so.0 => /usr/lib/x86_64-linux-gnu/libwayland-server.so.0 (0x00007f5f9defc000)
	libgbm.so.1 => /usr/lib/x86_64-linux-gnu/libgbm.so.1 (0x00007f5f9dcf4000)
	libz.so.1 => /lib/x86_64-linux-gnu/libz.so.1 (0x00007f5f9dadb000)
	librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007f5f9d8d3000)
	libXrandr.so.2 => /usr/lib/x86_64-linux-gnu/libXrandr.so.2 (0x00007f5f9d6c9000)
	libXinerama.so.1 => /usr/lib/x86_64-linux-gnu/libXinerama.so.1 (0x00007f5f9d4c6000)
	libXcursor.so.1 => /usr/lib/x86_64-linux-gnu/libXcursor.so.1 (0x00007f5f9d2bc000)
	libXau.so.6 => /usr/lib/x86_64-linux-gnu/libXau.so.6 (0x00007f5f9d0b8000)
	libXdmcp.so.6 => /usr/lib/x86_64-linux-gnu/libXdmcp.so.6 (0x00007f5f9ceb2000)
	libffi.so.6 => /usr/lib/x86_64-linux-gnu/libffi.so.6 (0x00007f5f9ccaa000)
	libXrender.so.1 => /usr/lib/x86_64-linux-gnu/libXrender.so.1 (0x00007f5f9caa0000)

    Any help is appreciated.

    opened by playerkk 10
  • random sample generation

    random sample generation

    I'm trying to figure out how I can multithread the loading of these houses, since the metadata (JSON) processing in house.py is taking the most amount of time when trying to iterate through a lot of houses. I was trying this code out (apologies for being a bit messy, but you can start looking @ L139 of test-samples.py). When I run this code, though, it results in a segfault as soon as I start trying to render images (L149). Do you have any idea what I could try to fix this issue?

    opened by mr-lubo 9
  • Floor/walls not rendered, camera only rotates in test-env.py

    Floor/walls not rendered, camera only rotates in test-env.py

    I am using the provided Dockerfile and running test-env.py on house 0a0b9b45a1db29832dd84e80c1347854

    1. Why aren't the walls/floors being rendered properly, but everything else is? screenshot from 2018-11-05 18-31-33

    2. I am running test-env.py and the camera rotates when I press h or l but doesn't move when I use wasd.

    opened by mfe7 5
  • Error while running test-rendering.py

    Error while running test-rendering.py

    I get an error when I try to run the python tests: python test-rendering.py house.obj

    [EGL] Detected 2 devices. Using device 0
error: ERROR::FRAMEBUFFER: Framebuffer is not complete!

    I read the common issues, I am not running any other renderer.

    I am running House3D inside a docker.

    opened by devendrachaplot 5
  • Even faster approximate initialization

    Even faster approximate initialization

    This depends on the other diff, but I tested this with a sample of the SUNCG dataset and it seems to produce okay results. This just uses cv2 morphological operations and numpy to do some more approximate move map computation instead of trying to do fine-grained collision checking using pure python

    opened by mr-lubo 5
  • ImportError: dynamic module does not define module export function (PyInit_objrender)

    ImportError: dynamic module does not define module export function (PyInit_objrender)

    Hello, I have been building the renderer as instructed in House3D/renderer/README.md. When I tried checking whether the renderer works successfully by running python test-rendering.py (The corresponding house.obj file has already been created), I get the following results.

    [email protected]:~/House3D/tests$ export PYTHONPATH=..
[email protected]:~/House3D/tests$ python test-rendering.py /home/kbkim/suncg_data/house/00065ecbdd7300d35ef4328ffe871505/house.obj
Traceback (most recent call last):
  File "test-rendering.py", line 12, in <module>
    from House3D import objrender, create_default_config
  File "/home/kbkim/House3D/House3D/__init__.py", line 6, in <module>
    from .core import Environment, MultiHouseEnv
  File "/home/kbkim/House3D/House3D/core.py", line 17, in <module>
    from .objrender import RenderMode
ImportError: dynamic module does not define module export function (PyInit_objrender)
Error in sys.excepthook:
Traceback (most recent call last):
  File "/usr/lib/python3/dist-packages/apport_python_hook.py", line 63, in apport_excepthook
    from apport.fileutils import likely_packaged, get_recent_crashes
  File "/usr/lib/python3/dist-packages/apport/__init__.py", line 5, in <module>
    from apport.report import Report
  File "/usr/lib/python3/dist-packages/apport/report.py", line 30, in <module>
    import apport.fileutils
  File "/usr/lib/python3/dist-packages/apport/fileutils.py", line 23, in <module>
    from apport.packaging_impl import impl as packaging
  File "/usr/lib/python3/dist-packages/apport/packaging_impl.py", line 23, in <module>
    import apt
  File "/usr/lib/python3/dist-packages/apt/__init__.py", line 23, in <module>
    import apt_pkg
ModuleNotFoundError: No module named 'apt_pkg'

Original exception was:
Traceback (most recent call last):
  File "test-rendering.py", line 12, in <module>
    from House3D import objrender, create_default_config
  File "/home/kbkim/House3D/House3D/__init__.py", line 6, in <module>
    from .core import Environment, MultiHouseEnv
  File "/home/kbkim/House3D/House3D/core.py", line 17, in <module>
    from .objrender import RenderMode
ImportError: dynamic module does not define module export function (PyInit_objrender)

    As for the missing module 'apt_pkg', I have not found any other solution than apt-get install python-apt (as described here), which has not changed my error message either.

    I have Python 3.6.7, and cv2.__version__ gives '4.0.0'.

    The OS, NVidia driver versions are as follows.

    [email protected]:~$ lsb_release -a
No LSB modules are available.
Distributor ID: Ubuntu
Description:    Ubuntu 16.04.5 LTS
Release:        16.04
Codename:       xenial
[email protected]:~/House3D/tests$ nvidia-smi
Mon Jan 14 16:57:03 2019
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 384.130                Driver Version: 384.130                   |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  TITAN V             On   | 00000000:18:00.0 Off |                  N/A |
| 36%   51C    P8    33W / 250W |      0MiB / 12058MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
|   1  TITAN V             On   | 00000000:3B:00.0 Off |                  N/A |
| 40%   57C    P8    36W / 250W |      0MiB / 12058MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
|   2  TITAN V             On   | 00000000:86:00.0 Off |                  N/A |
| 38%   54C    P8    29W / 250W |      0MiB / 12058MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
|   3  TITAN V             On   | 00000000:AF:00.0 Off |                  N/A |
| 41%   58C    P8    33W / 250W |      0MiB / 12058MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

    Running debug-build.sh gives the following output.

    [email protected]:~/House3D/renderer$ ./debug-build.sh
PATH:
/home/kbkim/bin:/home/kbkim/.local/bin:/usr/local/cuda-9.0/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin

CPATH:


PKG_CONFIG_PATH:


LIBRARY_PATH:


LD_LIBRARY_PATH:
/usr/local/cuda-9.0/lib64:

PYTHONPATH:
..

ldconfig:
        libEGL_nvidia.so.0 (libc6,x86-64) => /usr/lib/nvidia-384/libEGL_nvidia.so.0
        libEGL_nvidia.so.0 (libc6) => /usr/lib32/nvidia-384/libEGL_nvidia.so.0
        libEGL.so.1 (libc6,x86-64) => /usr/lib/nvidia-384/libEGL.so.1
        libEGL.so.1 (libc6) => /usr/lib32/nvidia-384/libEGL.so.1
        libEGL.so (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libEGL.so
        libEGL.so (libc6,x86-64) => /usr/lib/nvidia-384/libEGL.so
        libEGL.so (libc6) => /usr/lib32/nvidia-384/libEGL.so
+ pkg-config --cflags --libs glfw3
-I/usr/include/libdrm -lglfw
+ '[' '!' '' ']'
+ pkg-config --cflags --libs libglvnd
-I/usr/local/include
+ pkg-config --cflags --libs egl
-I/usr/include/libdrm -lEGL
+ which find
/usr/bin/find
+ which pkg-config
/usr/bin/pkg-config
+ which python-config
/usr/bin/python-config
+ python-config --includes --ldflags
-I/usr/include/python2.7 -I/usr/include/x86_64-linux-gnu/python2.7
-L/usr/lib/python2.7/config-x86_64-linux-gnu -L/usr/lib -lpython2.7 -lpthread -ldl  -lutil -lm  -Xlinker -export-dynamic -Wl,-O1 -Wl,-Bsymbolic-functions
+ '[' ']'
+ g++ --version
g++ (Ubuntu 5.4.0-6ubuntu1~16.04.11) 5.4.0 20160609
Copyright (C) 2015 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.

+ '[' -f ../House3D/objrender.so ']'
+ ldd ../House3D/objrender.so
        linux-vdso.so.1 =>  (0x00007ffc1d558000)
        libGL.so.1 => /usr/local/lib/libGL.so.1 (0x00007fa83a6ec000)
        libEGL.so.1 => /usr/lib/nvidia-384/libEGL.so.1 (0x00007fa83a4e7000)
        libX11.so.6 => /usr/lib/x86_64-linux-gnu/libX11.so.6 (0x00007fa83a1ad000)
        libpng12.so.0 => /lib/x86_64-linux-gnu/libpng12.so.0 (0x00007fa839f87000)
        libglfw.so.3 => /usr/lib/x86_64-linux-gnu/libglfw.so.3 (0x00007fa839d71000)
        libjpeg.so.8 => /usr/lib/x86_64-linux-gnu/libjpeg.so.8 (0x00007fa839b18000)
        libpython2.7.so.1.0 => /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0 (0x00007fa839589000)
        libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007fa83936c000)
        libstdc++.so.6 => /usr/lib/x86_64-linux-gnu/libstdc++.so.6 (0x00007fa838fea000)
        libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007fa838ce0000)
        libgcc_s.so.1 => /lib/x86_64-linux-gnu/libgcc_s.so.1 (0x00007fa838aca000)
        libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007fa838700000)
        /lib64/ld-linux-x86-64.so.2 (0x000056458ad58000)
        libGLX.so.0 => /usr/local/lib/libGLX.so.0 (0x00007fa8384c3000)
        libGLdispatch.so.0 => /usr/local/lib/libGLdispatch.so.0 (0x00007fa838208000)
        libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007fa838004000)
        libxcb.so.1 => /usr/lib/x86_64-linux-gnu/libxcb.so.1 (0x00007fa837de1000)
        libz.so.1 => /lib/x86_64-linux-gnu/libz.so.1 (0x00007fa837bc7000)
        librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007fa8379bf000)
        libXrandr.so.2 => /usr/lib/x86_64-linux-gnu/libXrandr.so.2 (0x00007fa8377b3000)
        libXinerama.so.1 => /usr/lib/x86_64-linux-gnu/libXinerama.so.1 (0x00007fa8375b0000)
        libXi.so.6 => /usr/lib/x86_64-linux-gnu/libXi.so.6 (0x00007fa8373a0000)
        libXxf86vm.so.1 => /usr/lib/x86_64-linux-gnu/libXxf86vm.so.1 (0x00007fa837199000)
        libXcursor.so.1 => /usr/lib/x86_64-linux-gnu/libXcursor.so.1 (0x00007fa836f8f000)
        libutil.so.1 => /lib/x86_64-linux-gnu/libutil.so.1 (0x00007fa836d8c000)
        libXau.so.6 => /usr/lib/x86_64-linux-gnu/libXau.so.6 (0x00007fa836b87000)
        libXdmcp.so.6 => /usr/lib/x86_64-linux-gnu/libXdmcp.so.6 (0x00007fa836981000)
        libXext.so.6 => /usr/lib/x86_64-linux-gnu/libXext.so.6 (0x00007fa83676e000)
        libXrender.so.1 => /usr/lib/x86_64-linux-gnu/libXrender.so.1 (0x00007fa836564000)
        libXfixes.so.3 => /usr/lib/x86_64-linux-gnu/libXfixes.so.3 (0x00007fa83635e000)

    Thank you in advance.

    opened by lionminhu 4
  • Error: cannot reslove

    Error: cannot reslove "Assertion "glGetString(GL_VERSION)" FAILED" after trying all possible issue

    1. ubuntu 16.04 with nvidia 1080Ti, 396.44
    sudo apt install libglfw3-dev libglm-dev libx11-dev libegl1-mesa-dev libpng-dev libjpeg-dev
cd
git clone https://github.com/NVIDIA/libglvnd && cd libglvnd
./autogen.sh && ./configure --disable-egl
make -j && sudo make install -j

    PATH:
/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/home/jiayi/.local/bin

CPATH:


PKG_CONFIG_PATH:


LIBRARY_PATH:


LD_LIBRARY_PATH:


PYTHONPATH:


+ pkg-config --cflags --libs glfw3
-I/usr/include/libdrm -lglfw
+ '[' '!' '' ']'
+ pkg-config --cflags --libs libglvnd
-I/usr/local/include
+ pkg-config --cflags --libs egl
-I/usr/include/libdrm -lEGL
+ which find
/usr/bin/find
+ which pkg-config
/usr/bin/pkg-config
+ which python-config
/usr/bin/python-config
+ python-config --includes --ldflags
-I/usr/include/python2.7 -I/usr/include/x86_64-linux-gnu/python2.7
-L/usr/lib/python2.7/config-x86_64-linux-gnu -L/usr/lib -lpython2.7 -lpthread -ldl  -lutil -lm  -Xlinker -export-dynamic -Wl,-O1 -Wl,-Bsymbolic-functions
+ '[' ']'
+ g++ --version
g++ (Ubuntu 5.4.0-6ubuntu1~16.04.10) 5.4.0 20160609
Copyright (C) 2015 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.

+ '[' -f ../House3D/objrender.so ']'
+ ldd ../House3D/objrender.so
	linux-vdso.so.1 =>  (0x00007ffea73cc000)
	libGL.so.1 => /usr/lib/nvidia-396/libGL.so.1 (0x00007fc093a5e000)
	libEGL.so.1 => /usr/lib/nvidia-396/libEGL.so.1 (0x00007fc093858000)
	libX11.so.6 => /usr/lib/x86_64-linux-gnu/libX11.so.6 (0x00007fc09351e000)
	libpng12.so.0 => /lib/x86_64-linux-gnu/libpng12.so.0 (0x00007fc0932f8000)
	libglfw.so.3 => /usr/lib/x86_64-linux-gnu/libglfw.so.3 (0x00007fc0930e2000)
	libjpeg.so.8 => /usr/lib/x86_64-linux-gnu/libjpeg.so.8 (0x00007fc092e89000)
	libpython2.7.so.1.0 => /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0 (0x00007fc0928fa000)
	libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007fc0926dd000)
	libstdc++.so.6 => /usr/lib/x86_64-linux-gnu/libstdc++.so.6 (0x00007fc09235b000)
	libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007fc092051000)
	libgcc_s.so.1 => /lib/x86_64-linux-gnu/libgcc_s.so.1 (0x00007fc091e3b000)
	libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007fc091a71000)
	/lib64/ld-linux-x86-64.so.2 (0x000055d4ef045000)
	libnvidia-tls.so.396.44 => /usr/lib/nvidia-396/tls/libnvidia-tls.so.396.44 (0x00007fc09186c000)
	libnvidia-glcore.so.396.44 => /usr/lib/nvidia-396/libnvidia-glcore.so.396.44 (0x00007fc08fb9d000)
	libXext.so.6 => /usr/lib/x86_64-linux-gnu/libXext.so.6 (0x00007fc08f98b000)
	libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007fc08f786000)
	libGLdispatch.so.0 => /usr/lib/nvidia-396/libGLdispatch.so.0 (0x00007fc08f4b8000)
	libxcb.so.1 => /usr/lib/x86_64-linux-gnu/libxcb.so.1 (0x00007fc08f296000)
	libz.so.1 => /lib/x86_64-linux-gnu/libz.so.1 (0x00007fc08f07b000)
	librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007fc08ee73000)
	libXrandr.so.2 => /usr/lib/x86_64-linux-gnu/libXrandr.so.2 (0x00007fc08ec68000)
	libXinerama.so.1 => /usr/lib/x86_64-linux-gnu/libXinerama.so.1 (0x00007fc08ea64000)
	libXi.so.6 => /usr/lib/x86_64-linux-gnu/libXi.so.6 (0x00007fc08e854000)
	libXxf86vm.so.1 => /usr/lib/x86_64-linux-gnu/libXxf86vm.so.1 (0x00007fc08e64e000)
	libXcursor.so.1 => /usr/lib/x86_64-linux-gnu/libXcursor.so.1 (0x00007fc08e443000)
	libutil.so.1 => /lib/x86_64-linux-gnu/libutil.so.1 (0x00007fc08e240000)
	libXau.so.6 => /usr/lib/x86_64-linux-gnu/libXau.so.6 (0x00007fc08e03b000)
	libXdmcp.so.6 => /usr/lib/x86_64-linux-gnu/libXdmcp.so.6 (0x00007fc08de35000)
	libXrender.so.1 => /usr/lib/x86_64-linux-gnu/libXrender.so.1 (0x00007fc08dc2b000)
	libXfixes.so.3 => /usr/lib/x86_64-linux-gnu/libXfixes.so.3 (0x00007fc08da24000)
    1. after typing command unset DISPLAY
    ➜  renderer git:(master) unset DISPLAY
➜  renderer git:(master) ./test-rectangle.bin egl     
[EGL] Detected 8 devices. Using device 0
assertion "glGetString(GL_VERSION)" failed, in printInfo, (gl/glContext.cc:92)
[1]    52092 abort (core dumped)  ./test-rectangle.bin egl
➜  renderer git:(master) ./test-rectangle.bin headless
error: Cannot connect to DISPLAY!
➜  renderer git:(master)

    More info:

    ➜  renderer git:(master) ./objview-offline.bin /data/.share/suncg/house/bd4d249bb93e43e023f7fa2ff30fa0b1/house.obj
[EGL] Detected 8 devices. Using device 0
assertion "glGetString(GL_VERSION)" failed, in printInfo, (gl/glContext.cc:92)
[1]    52610 abort (core dumped)  ./objview-offline.bin

    and use ssh -X command:

    ➜  ~ glxinfo
name of display: localhost:11.0
X Error of failed request:  BadValue (integer parameter out of range for operation)
  Major opcode of failed request:  155 (GLX)
  Minor opcode of failed request:  24 (X_GLXCreateNewContext)
  Value in failed request:  0x0
  Serial number of failed request:  35
  Current serial number in output stream:  36

    I also try to install virtualGL as one issue suggested, however it seems unsuccessful in my machine. I'm so confused that I only type the command listed in README.md but failed to build. I have reinstalled all the dependency but no promising things happened. Any help?

    opened by Trinkle23897 4
  • error while running Dockerfile

    error while running Dockerfile

    hi, I've just run the Dockerfile in ubuntu 14.04 system with nvida gpu, and got following error in the terminal:

    [dep]test-rectangle.cpp ... Packge gl was not found in the pkg-config serach path. Perhaps you should add the directory containing 'gl.pc' to the PKG_CONFIG_PATH environment variable No package 'gl' found Packge egl was not found in the pkg-config serach path. Perhaps you should add the directory containing 'egl.pc' to the PKG_CONFIG_PATH environment variable No package 'x11' found Packge x11 was not found in the pkg-config serach path. Perhaps you should add the directory containing 'x11.pc' to the PKG_CONFIG_PATH environment variable No package 'x11' found [dep]objvie-offline.cpp ... Packge gl was not found in the pkg-config serach path. Perhaps you should add the directory containing 'gl.pc' to the PKG_CONFIG_PATH environment variable No package 'gl' found Packge egl was not found in the pkg-config serach path. Perhaps you should add the directory containing 'egl.pc' to the PKG_CONFIG_PATH environment variable No package 'x11' found Packge x11 was not found in the pkg-config serach path. Perhaps you should add the directory containing 'x11.pc' to the PKG_CONFIG_PATH environment variable No package 'x11' found ...

    I already installed opencv and related libraries, and the 'gl.pc', 'egl.pc', 'x11.pc' these files have been copied to the pkg-config serach path. Still it reports these error. Thanks in advance

    opened by wwwqqqqq 4
  • Target $I$ for the Gated-LSTM baseline

    Target $I$ for the Gated-LSTM baseline

    Hello, I have been trying to implement the Gated-LSTM baseline according to the descriptions in the RoomNav paper (link), but I am confused with the some of the notations.

    From Section 5.2.2 (for Gated-LSTM): image

    The symbol $I$ is used to denote the target instruction. This same symbol was used in Section 5.1.2 (for Gated-CNN) to denote the target instruction prior to conversion to an embedding vector $y$: image

    So if we were to follow the same notation as in Section 5.1.2, we would have to feed the one-hot vector $I$ (and not the embedding vector) as input to the gated fusion module and the LSTM for the Gated-LSTM.

    However, the Figure 2 seems to imply that it is in fact the embedding vector that is fed into the gated fusion and the LSTM: image

    Could you clarify whether the target $I$ for Gated-LSTM baseline is meant to be the one-hot vector or the embedding vector?

    Thank you in advance.

    opened by lionminhu 4
  • meet error: ERROR::FRAMEBUFFER: Framebuffer is not complete! ErrorCode=36061 when execute test-rendering.py

    meet error: ERROR::FRAMEBUFFER: Framebuffer is not complete! ErrorCode=36061 when execute test-rendering.py

    when I execute test-rendering.py, I meet error:error: ERROR::FRAMEBUFFER: Framebuffer is not complete! ErrorCode=36061 1.Nvidia GTX 1080Ti,Ubuntu16.04; 2.I build by docker; 3.When I execute cd /House3D/tests && python3 test-rendering.py $TEST_HOUSE --interactive,Error occur:ERROR::FRAMEBUFFER: Framebuffer is not complete! ErrorCode=36061; And i find error occur when it execute "api = objrender.RenderAPI(w=600, h=450, device=0)"(ln13) 4.after i execute debug-build.sh,result: PATH: /usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin

    CPATH:

    PKG_CONFIG_PATH:

    LIBRARY_PATH:

    LD_LIBRARY_PATH: /usr/lib/x86_64-linux-gnu:/usr/lib/i386-linux-gnu:/usr/local/nvidia/lib:/usr/local/nvidia/lib64

    PYTHONPATH:

    DISPLAY: :0

    ldconfig: libEGL_nvidia.so.0 (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libEGL_nvidia.so.0 libEGL_nvidia.so.0 (libc6) => /usr/lib/i386-linux-gnu/libEGL_nvidia.so.0 libEGL_mesa.so.0 (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libEGL_mesa.so.0 libEGL_mesa.so.0 (libc6) => /usr/lib/i386-linux-gnu/libEGL_mesa.so.0 libEGL.so.1 (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libEGL.so.1 libEGL.so.1 (libc6) => /usr/lib/i386-linux-gnu/libEGL.so.1 libEGL.so (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libEGL.so libEGL.so (libc6) => /usr/lib/i386-linux-gnu/libEGL.so

    • pkg-config --cflags --libs glfw3 -lglfw

    • '[' '!' '' ']'

    • pkg-config --cflags --libs libglvnd

    • pkg-config --cflags --libs egl -I/usr/include/libdrm -lEGL

    • which find /usr/bin/find

    • which pkg-config /usr/bin/pkg-config

    • which python3-config /usr/bin/python3-config

    • python3-config --includes --ldflags -I/usr/include/python3.6m -I/usr/include/python3.6m -L/usr/lib/python3.6/config-3.6m-x86_64-linux-gnu -L/usr/lib -lpython3.6m -lpthread -ldl -lutil -lm -Xlinker -export-dynamic -Wl,-O1 -Wl,-Bsymbolic-functions

    • '[' ']'

    • g++ --version g++ (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0 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.

    • '[' -f ../House3D/objrender.so ']'

    • ldd ../House3D/objrender.so linux-vdso.so.1 (0x00007ffc6c9dd000) libGL.so.1 => /usr/lib/x86_64-linux-gnu/libGL.so.1 (0x00007f852d3f4000) libEGL.so.1 => /usr/lib/x86_64-linux-gnu/libEGL.so.1 (0x00007f852d1e0000) libX11.so.6 => /usr/lib/x86_64-linux-gnu/libX11.so.6 (0x00007f852cea8000) libpng16.so.16 => /usr/lib/x86_64-linux-gnu/libpng16.so.16 (0x00007f852cc76000) libglfw.so.3 => /usr/lib/x86_64-linux-gnu/libglfw.so.3 (0x00007f852ca59000) libjpeg.so.8 => /usr/lib/x86_64-linux-gnu/libjpeg.so.8 (0x00007f852c7f1000) libpython3.6m.so.1.0 => /usr/lib/x86_64-linux-gnu/libpython3.6m.so.1.0 (0x00007f852c13f000) libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007f852bf20000) libstdc++.so.6 => /usr/lib/x86_64-linux-gnu/libstdc++.so.6 (0x00007f852bb97000) libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007f852b7f9000) libgcc_s.so.1 => /lib/x86_64-linux-gnu/libgcc_s.so.1 (0x00007f852b5e1000) libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f852b1f0000) /lib64/ld-linux-x86-64.so.2 (0x00007f852d984000) libGLX.so.0 => /usr/lib/x86_64-linux-gnu/libGLX.so.0 (0x00007f852afbf000) libGLdispatch.so.0 => /usr/lib/x86_64-linux-gnu/libGLdispatch.so.0 (0x00007f852ad09000) libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007f852ab05000) libxcb.so.1 => /usr/lib/x86_64-linux-gnu/libxcb.so.1 (0x00007f852a8dd000) libz.so.1 => /lib/x86_64-linux-gnu/libz.so.1 (0x00007f852a6c0000) librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007f852a4b8000) libXrandr.so.2 => /usr/lib/x86_64-linux-gnu/libXrandr.so.2 (0x00007f852a2ad000) libXinerama.so.1 => /usr/lib/x86_64-linux-gnu/libXinerama.so.1 (0x00007f852a0aa000) libXxf86vm.so.1 => /usr/lib/x86_64-linux-gnu/libXxf86vm.so.1 (0x00007f8529ea4000) libXcursor.so.1 => /usr/lib/x86_64-linux-gnu/libXcursor.so.1 (0x00007f8529c9a000) libexpat.so.1 => /lib/x86_64-linux-gnu/libexpat.so.1 (0x00007f8529a68000) libutil.so.1 => /lib/x86_64-linux-gnu/libutil.so.1 (0x00007f8529865000) libXau.so.6 => /usr/lib/x86_64-linux-gnu/libXau.so.6 (0x00007f8529661000) libXdmcp.so.6 => /usr/lib/x86_64-linux-gnu/libXdmcp.so.6 (0x00007f852945b000) libXext.so.6 => /usr/lib/x86_64-linux-gnu/libXext.so.6 (0x00007f8529249000) libXrender.so.1 => /usr/lib/x86_64-linux-gnu/libXrender.so.1 (0x00007f852903f000) libXfixes.so.3 => /usr/lib/x86_64-linux-gnu/libXfixes.so.3 (0x00007f8528e39000) libbsd.so.0 => /lib/x86_64-linux-gnu/libbsd.so.0 (0x00007f8528c24000)

    opened by gitwld 6
  • The SUNCG dataset is not available now

    The SUNCG dataset is not available now

    As discussed in:

    • https://github.com/minosworld/minos/issues/159
    • https://github.com/shurans/SUNCGtoolbox/issues/32
    • https://github.com/HoME-Platform/home-platform/issues/30

    All links are dead for the dataset.

    opened by hzxie 7
  • Cache houses

    Cache houses

    Hi, How can we go about caching houses? I see there is a reference to a script named cache_houses.py, but I don't see it in the repo. It will be very helpful because currently the MultiHouseEnv takes forever to load with more than 5 houses or so.

    Best, Amanjit

    opened by amanjitsk 0
  • How to get and set the fx and fy of the camera from the test-rendering？

    How to get and set the fx and fy of the camera from the test-rendering？

    Is there any way to get or set the parameter of the camera in test-rendering (python file). And the which kind of device in parser.add_argument('--device', type=int, default=0) can be set?

    opened by jiajialu1995 2
  • Step on multiple environment in parallel

    Step on multiple environment in parallel

    Hi, thanks for open sourcing this code.

    I am wondering whether we can load multiple environments and then step on them in parallel? It will be extremely useful to accelerate the data loading process.

    thanks!

    opened by jwyang 8
Owner
Meta Research
Meta Research
GitHub Repository
This repository is the official implementation of Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning (NeurIPS21).

Core-tuning This repository is the official implementation of ``Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regular

vanint 18 Dec 17, 2022
Code repository for the paper: Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild (ICCV 2021)

Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild Akash Sengupta, Ignas Budvytis, Robert

Akash Sengupta 149 Dec 14, 2022
Flower classification model that classifies flowers in 10 classes made using transfer learning (~85% accuracy).

flower-classification-inceptionV3 Flower classification model that classifies flowers in 10 classes. Training and validation are done using a pre-anot

Ivan R. Mršulja 1 Dec 12, 2021
Accelerated deep learning R&D

Accelerated deep learning R&D PyTorch framework for Deep Learning research and development. It focuses on reproducibility, rapid experimentation, and

Catalyst-Team 3.1k Jan 06, 2023
Pytorch Lightning Distributed Accelerators using Ray

Distributed PyTorch Lightning Training on Ray This library adds new PyTorch Lightning plugins for distributed training using the Ray distributed compu

167 Jan 02, 2023
This project provides the code and datasets for 'CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection', CVPR 2019.

Code-and-Dataset-for-CapSal This project provides the code and datasets for 'CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detec

lu zhang 48 Aug 19, 2022
This is an official repository of CLGo: Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints

CLGo This is an official repository of CLGo: Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints An earlier

刘芮金 32 Dec 20, 2022
an implementation of Revisiting Adaptive Convolutions for Video Frame Interpolation using PyTorch

revisiting-sepconv This is a reference implementation of Revisiting Adaptive Convolutions for Video Frame Interpolation [1] using PyTorch. Given two f

Simon Niklaus 59 Dec 22, 2022
Pytorch implementation AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks

AttnGAN Pytorch implementation for reproducing AttnGAN results in the paper AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative

Tao Xu 1.2k Dec 26, 2022
This is the implementation of the paper "Self-supervised Outdoor Scene Relighting"

Self-supervised Outdoor Scene Relighting This is the implementation of the paper "Self-supervised Outdoor Scene Relighting". The model is implemented

Ye Yu 24 Dec 17, 2022
Decorators for maximizing memory utilization with PyTorch & CUDA

torch-max-mem This package provides decorators for memory utilization maximization with PyTorch and CUDA by starting with a maximum parameter size and

Max Berrendorf 10 May 02, 2022
[CVPR 2021] 'Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator'

[CVPR2021] Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator Overview This is the entire codebase for the paper

35 Dec 01, 2022
Second-Order Neural ODE Optimizer, NeurIPS 2021 spotlight

Second-order Neural ODE Optimizer (NeurIPS 2021 Spotlight) [arXiv] ✔️ faster convergence in wall-clock time | ✔️ O(1) memory cost | ✔️ better test-tim

Guan-Horng Liu 39 Oct 22, 2022
A library for Deep Learning Implementations and utils

deeply A Deep Learning library Table of Contents Features Quick Start Usage License Features Python 2.7+ and Python 3.4+ compatible. Quick Start $ pip

Achilles Rasquinha 1 Dec 12, 2022
This is a Pytorch implementation of paper: DropEdge: Towards Deep Graph Convolutional Networks on Node Classification

DropEdge: Towards Deep Graph Convolutional Networks on Node Classification This is a Pytorch implementation of paper: DropEdge: Towards Deep Graph Con

401 Dec 16, 2022
Applying curriculum to meta-learning for few shot classification

Curriculum Meta-Learning for Few-shot Classification We propose an adaptation of the curriculum training framework, applicable to state-of-the-art met

Stergiadis Manos 3 Oct 25, 2022
Stochastic gradient descent with model building

Stochastic Model Building (SMB) This repository includes a new fast and robust stochastic optimization algorithm for training deep learning models. Th

S. Ilker Birbil 22 Jan 19, 2022
PyTorch implementation of paper “Unbiased Scene Graph Generation from Biased Training”

A new codebase for popular Scene Graph Generation methods (2020). Visualization & Scene Graph Extraction on custom images/datasets are provided. It's also a PyTorch implementation of paper “Unbiased

Kaihua Tang 824 Jan 03, 2023
NeWT: Natural World Tasks

NeWT: Natural World Tasks This repository contains resources for working with the NeWT dataset. ❗ At this time the binary tasks are not publicly avail

Visipedia 26 Oct 18, 2022
docTR by Mindee (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

docTR by Mindee (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

Mindee 1.5k Jan 01, 2023