Data for eval.py script

[VolodymyrAhafonov]

Hello, very interesting paper and promising results! Could you please provide test data for eval.py. I want to try out your matting network.

Kind regards, Vladimir.

[Windaway]

You can create three folders merged, trimap, and alpha, then put images in folders merged and trimap. LFPNet works better on high-resolution images.

[VolodymyrAhafonov]

@Windaway thank you for your reply. I've done it. But I've got bad results. So that's why I've requested test data from you.

[Windaway]

Thank you for your feedback. The code runs normally on my computer and training server. Below are the test images (no ground truth) and our results. I think the code may depend on a specific version of the python library. You may build a new environment according to my configuration.

absl-py==0.9.0 addict==2.4.0 apturl==0.5.2 asn1crypto==0.24.0 astor==0.8.0 attrs==19.3.0 backcall==0.1.0 beautifulsoup4==4.6.0 bleach==3.1.0 Brlapi==0.6.6 certifi==2018.1.18 chardet==3.0.4 chumpy==0.69 Click==7.0 codecov==2.1.11 colorama==0.4.4 command-not-found==0.3 ConfigArgParse==0.15.1 configer==1.4.1 configparser==4.0.2 coverage==5.5 cryptography==2.1.4 cupshelpers==1.0 cycler==0.10.0 Cython==0.29.14 decorator==4.4.1 defer==1.0.6 defusedxml==0.6.0 distro-info===0.18ubuntu0.18.04.1 entrypoints==0.3 flake8==3.8.4 freetype-py==2.1.0.post1 future==0.18.2 gast==0.3.2 grpcio==1.25.0 h5py==2.7.1 homogenus===.5 html5lib==0.999999999 httplib2==0.9.2 human-body-prior==0.9.3.0 idna==2.6 imageio==2.6.1 imageio-ffmpeg==0.3.0 imgaug==0.4.0 importlib-metadata==0.23 iniconfig==1.1.1 interrogate==1.3.2 ipykernel==5.1.3 ipython==7.9.0 ipython-genutils==0.2.0 ipywidgets==7.5.1 isort==4.3.21 jedi==0.15.1 Jinja2==2.10.3 jsonpatch==1.25 jsonpointer==2.0 jsonschema==3.1.1 jupyter-client==5.3.4 jupyter-core==4.6.1 Keras-Applications==1.0.8 Keras-Preprocessing==1.1.0 keyring==10.6.0 keyrings.alt==3.0 kiwisolver==1.1.0 kornia==0.4.0 language-selector==0.1 launchpadlib==1.10.6 lazr.restfulclient==0.13.5 lazr.uri==1.0.3 leveldb==0.1 llvmlite==0.32.1 lmdb==1.1.1 louis==3.5.0 lxml==4.2.1 macaroonbakery==1.1.3 Mako==1.0.7 Markdown==3.1.1 MarkupSafe==1.1.1 matplotlib==3.1.2 mccabe==0.6.1 mesh-intersection==0.1.0 mistune==0.8.4 mmcv-full==1.2.6 -e git+https://gitee.com/mirrors/mmdetection.git@247785ceb31cabb0e3fd4c6ce17108d04f478ab8#egg=mmdet -e git+https://github.com/open-mmlab/mmediting.git@4c2345f6daa57ecb87f5fdb3c8e0ffa60993d83c#egg=mmedit mmpycocotools==12.0.3 mock==3.0.5 more-itertools==7.2.0 moviepy==1.0.1 nbconvert==5.6.1 nbformat==4.4.0 netifaces==0.10.4 networkx==2.4 nose==1.3.7 notebook==6.0.2 numba==0.49.1 numexpr==2.6.4 numpy==1.17.4 oauth==1.0.1 olefile==0.45.1 open3d-python==0.7.0.0 opencv-python==4.2.0.34 opendr==0.78 packaging==20.9 pandas==0.22.0 pandocfilters==1.4.2 parso==0.5.1 pexpect==4.7.0 pickleshare==0.7.5 Pillow==6.2.2 pluggy==0.13.1 proglog==0.1.9 prometheus-client==0.7.1 prompt-toolkit==2.0.10 protobuf==3.11.2 ptyprocess==0.6.0 py==1.10.0 pycairo==1.16.2 pycocotools==2.0.0 pycodestyle==2.6.0 pycrypto==2.6.1 pycups==1.9.73 pyflakes==2.2.0 pyglet==1.4.0b1 Pygments==2.4.2 pygobject==3.26.1 pymacaroons==0.13.0 PyMatting==1.0.6 PyNaCl==1.1.2 PyOpenGL==3.1.0 pyparsing==2.4.6 pyrender==0.1.32 pyRFC3339==1.0 pyrsistent==0.15.5 pytest==6.2.2 pytest-runner==5.3.0 python-apt==1.6.5+ubuntu0.5 python-dateutil==2.8.1 python-debian==0.1.32 python-gflags==1.5.1 pythotk==0.2 pytz==2018.3 PyWavelets==1.1.1 pyxdg==0.25 PyYAML==5.1 pyzmq==18.1.0 reportlab==3.4.0 requests==2.18.4 requests-unixsocket==0.1.5 scikit-image==0.16.2 scikit-learn==0.20.3 scipy==1.3.2 screen-resolution-extra==0.0.0 SecretStorage==2.3.1 Send2Trash==1.5.0 Shapely==1.6.4.post2 simplegeneric==0.8.1 simplejson==3.13.2 six==1.13.0 smplx==0.1.13 system-service==0.3 systemd-python==234 tables==3.4.2 tabulate==0.8.9 tensorboard==1.13.1 tensorboardX==2.0 tensorflow==1.13.1 tensorflow-estimator==1.13.0 termcolor==1.1.0 terminado==0.8.3 terminaltables==3.1.0 testpath==0.4.4 toml==0.10.2 torch==1.6.0 torchfile==0.1.0 torchgeometry==0.1.2 torchnet==0.0.5.1 torchsummary==1.5.1 torchvision==0.7.0 tornado==6.0.3 tqdm==4.38.0 traitlets==4.3.3 transforms3d==0.3.1 trimesh==3.4.1 ubuntu-drivers-common==0.0.0 ufw==0.36 unattended-upgrades==0.1 urllib3==1.22 usb-creator==0.3.3 visdom==0.1.8.9 wadllib==1.3.2 wcwidth==0.1.7 webencodings==0.5.1 websocket-client==0.57.0 Werkzeug==0.16.0 widgetsnbextension==3.5.1 xkit==0.0.0 yacs==0.1.7 yapf==0.30.0 youtube-dl==2019.11.5 zipp==0.6.0 zope.interface==4.3.2

[Windaway]

Here is the result of FBAMatting.

[VolodymyrAhafonov]

@Windaway thank you very much for provided images! I've reproduced same results with provided images. And also found root cause of issue with my data.

[VolodymyrAhafonov]

We can close issue now.

[hackkhai]

@VolodymyrAhafonov What was the problem that you faced with your data?

[VolodymyrAhafonov]

@hackkhai Unknown (grey) area was equal to 127 in my trimap. Eval script expect that unknown area is equal to 128.