nyummvc / cpd-net Goto Github PK

hi!
i want to add some feature processing module follow your feature descriptors in pytorch, and i foud it's hard to sovle this problem.
Could you give me some advice ?

and i have another question
v2=v1.sg_conv(dim=64, size=(1,1), name='gen1',pad="SAME",bn=True)

conv2 = torch.nn.conv2d(16,64,kernel_size=(1,1), bias=True, padding=0)
bn2 = nn.BatchNorm2d(64)
bn2(conv2(v1)

are these two equal ?
thank you

Hello there, I've run the code for 2d nonrigid point clouds registration, the performance is quite amazing with the default peremeters setting for source and target points. However, when I try to add outliers by setting outlier_ratio=1.1 to source points, as a result, the number of points in each source pointcloud is different, and the algorithm crashes at

write_to_tfrecords({"source": np.asanyarray([i.T for i in a.source_list])[np.random.choice(range(test_num), test_num)], "target": np.asanyarray([i.T for i in a.target_list])}, "temp_test_1.tfrecords")
more excatly, it happens becuase np.asanyarray cannot deal with elements with different shapes.

I read your paper and it's said that outliers are considered and the result seems great, so I'm here to look for some help, how can I modify the codes in order to cope with this problem?

first error is : " AttributeError: module 'tensorflow' has no attribute 'absolute_import' ", when I changeed the "/home/jax/anaconda3/lib/python3.6/site-packages/sugartensor/__init__.py" file :"from tensorflow import * " ==>" from tensorflow.python import * ", done!
then the bug is :

Training started with random seed: 111
Batch started with random seed: 111
*** Error in `python': free(): invalid pointer: 0x00005628fcf97488 ***
======= Backtrace: =========
/lib/x86_64-linux-gnu/libc.so.6(+0x777e5)[0x7fdbe57ce7e5]
/lib/x86_64-linux-gnu/libc.so.6(+0x8037a)[0x7fdbe57d737a]
/lib/x86_64-linux-gnu/libc.so.6(cfree+0x4c)[0x7fdbe57db53c]
/home/jax/anaconda3/lib/python3.6/site-packages/google/protobuf/pyext/../../../../../libprotobuf.so.19(_ZN6google8protobuf14DynamicMessageD2Ev+0x489)[0x7fdb3d1bb599]
/home/jax/anaconda3/lib/python3.6/site-packages/google/protobuf/pyext/../../../../../libprotobuf.so.19(_ZN6google8protobuf14DynamicMessageD0Ev+0xa)[0x7fdb3d1bb61a]
/home/jax/anaconda3/lib/python3.6/site-packages/google/protobuf/pyext/../../../../../libprotobuf.so.19(_ZN6google8protobuf14DynamicMessageD2Ev+0x1dd)[0x7fdb3d1bb2ed]
/home/jax/anaconda3/lib/python3.6/site-packages/google/protobuf/pyext/../../../../../libprotobuf.so.19(_ZN6google8protobuf14DynamicMessageD0Ev+0xa)[0x7fdb3d1bb61a]
/home/jax/anaconda3/lib/python3.6/site-packages/google/protobuf/pyext/_message.cpython-36m-x86_64-linux-gnu.so(+0x29f07)[0x7fdb3d324f07]
python(+0x19ae68)[0x5628f785fe68]
python(+0xf1b77)[0x5628f77b6b77]
python(+0x192e8b)[0x5628f7857e8b]
python(+0x193ed6)[0x5628f7858ed6]
python(+0x199b95)[0x5628f785eb95]
python(_PyEval_EvalFrameDefault+0x10cc)[0x5628f788251c]
python(+0x192e66)[0x5628f7857e66]
python(+0x193ed6)[0x5628f7858ed6]
。。。。。。。。。。。。。。。。。。。。。
/home/jax/anaconda3/lib/python3.6/site-packages/pandas/_libs/interval.cpython-36m-x86_64-linux-gnu.so
7fdb90350000-7fdb9035f000 rw-p 00233000 08:08 5902003 /home/jax/anaconda3/lib/python3.6/site-packages/pandas/_libs/interval.cpython-36m-x86_64-linu已放弃 (核心已转储)

my environment is :
name: tensorflow
channels:

• https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
• https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/msys2/
• https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge
• https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/
• https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
• defaults
  dependencies:
• _libgcc_mutex=0.1=main
• _pytorch_select=0.1=cpu_0
• _tflow_select=2.1.0=gpu
• absl-py=0.8.0=py36_0
• astor=0.7.1=py_0
• blas=1.0=mkl
• bzip2=1.0.8=h516909a_0
• c-ares=1.15.0=h516909a_1001
• ca-certificates=2019.6.16=hecc5488_0
• cairo=1.16.0=hfb77d84_1002
• certifi=2019.6.16=py36_1
• cffi=1.12.3=py36h8022711_0
• cudatoolkit=10.1.168=0
• cudnn=7.6.0=cuda10.1_0
• cupti=10.1.168=0
• cycler=0.10.0=py_1
• dbus=1.13.6=he372182_0
• expat=2.2.5=he1b5a44_1003
• ffmpeg=4.1.3=h167e202_0
• fontconfig=2.13.1=h86ecdb6_1001
• freetype=2.10.0=he983fc9_1
• gast=0.2.2=py_0
• gettext=0.19.8.1=hc5be6a0_1002
• giflib=5.1.9=h516909a_0
• glib=2.58.3=h6f030ca_1002
• gmp=6.1.2=hf484d3e_1000
• gnutls=3.6.5=hd3a4fd2_1002
• google-pasta=0.1.7=py_0
• graphite2=1.3.13=hf484d3e_1000
• grpcio=1.22.0=py36he9ae1f9_0
• gst-plugins-base=1.14.5=h0935bb2_0
• gstreamer=1.14.5=h36ae1b5_0
• h5py=2.9.0=nompi_py36h513d04c_1104
• harfbuzz=2.4.0=h9f30f68_3
• hdf5=1.10.5=nompi_h3c11f04_1103
• icu=64.2=he1b5a44_1
• intel-openmp=2019.4=243
• jasper=1.900.1=h07fcdf6_1006
• jpeg=9c=h14c3975_1001
• keras-applications=1.0.8=py_1
• keras-preprocessing=1.1.0=py_0
• kiwisolver=1.1.0=py36hc9558a2_0
• lame=3.100=h14c3975_1001
• libblas=3.8.0=12_mkl
• libcblas=3.8.0=12_mkl
• libedit=3.1.20181209=hc058e9b_0
• libffi=3.2.1=he1b5a44_1006
• libgcc-ng=9.1.0=hdf63c60_0
• libgfortran-ng=7.3.0=hdf63c60_0
• libiconv=1.15=h516909a_1005
• liblapack=3.8.0=12_mkl
• liblapacke=3.8.0=12_mkl
• libopenblas=0.3.7=h6e990d7_1
• libpng=1.6.37=hed695b0_0
• libprotobuf=3.9.1=h8b12597_0
• libstdcxx-ng=9.1.0=hdf63c60_0
• libtiff=4.0.10=h57b8799_1003
• libuuid=2.32.1=h14c3975_1000
• libwebp=1.0.2=h576950b_1
• libxcb=1.13=h14c3975_1002
• libxml2=2.9.9=hee79883_5
• lz4-c=1.8.3=he1b5a44_1001
• markdown=3.1.1=py_0
• matplotlib=3.1.1=py36_1
• matplotlib-base=3.1.1=py36he7580a8_1
• mkl=2019.4=243
• mkl-service=2.3.0=py36h516909a_0
• ncurses=6.1=hf484d3e_1002
• nettle=3.4.1=h1bed415_1002
• ninja=1.9.0=h6bb024c_0
• numpy=1.17.1=py36h95a1406_0
• opencv=4.1.1=py36ha799480_1
• openh264=1.8.0=hdbcaa40_1000
• openssl=1.1.1c=h516909a_0
• pcre=8.41=hf484d3e_1003
• pip=19.2.3=py36_0
• pixman=0.38.0=h516909a_1003
• protobuf=3.9.1=py36he1b5a44_0
• pthread-stubs=0.4=h14c3975_1001
• pycparser=2.19=py36_1
• pyparsing=2.4.2=py_0
• pyqt=5.9.2=py36hcca6a23_2
• python=3.6.9=h265db76_0
• python-dateutil=2.8.0=py_0
• pytorch=1.2.0=cpu_py36h00be3c6_0
• qt=5.9.7=h0c104cb_3
• readline=7.0=hf8c457e_1001
• scipy=1.3.1=py36h921218d_2
• setuptools=41.2.0=py36_0
• sip=4.19.8=py36hf484d3e_1000
• six=1.12.0=py36_1000
• sqlite=3.29.0=h7b6447c_0
• tensorboard=1.14.0=py36_0
• tensorflow=1.14.0=gpu_py36h3fb9ad6_0
• tensorflow-base=1.14.0=gpu_py36he45bfe2_0
• tensorflow-estimator=1.14.0=py36h5ca1d4c_0
• tensorflow-gpu=1.14.0=h0d30ee6_0
• termcolor=1.1.0=py_2
• tk=8.6.9=hed695b0_1002
• tornado=6.0.3=py36h516909a_0
• werkzeug=0.15.5=py_0
• wheel=0.33.6=py36_0
• wrapt=1.11.2=py36h516909a_0
• x264=1!152.20180806=h14c3975_0
• xorg-kbproto=1.0.7=h14c3975_1002
• xorg-libice=1.0.10=h516909a_0
• xorg-libsm=1.2.3=h84519dc_1000
• xorg-libx11=1.6.8=h516909a_0
• xorg-libxau=1.0.9=h14c3975_0
• xorg-libxdmcp=1.1.3=h516909a_0
• xorg-libxext=1.3.4=h516909a_0
• xorg-libxrender=0.9.10=h516909a_1002
• xorg-renderproto=0.11.1=h14c3975_1002
• xorg-xextproto=7.3.0=h14c3975_1002
• xorg-xproto=7.0.31=h14c3975_1007
• xz=5.2.4=h14c3975_1001
• zlib=1.2.11=h516909a_1005
• zstd=1.4.0=h3b9ef0a_0
  prefix: /home/jax/anaconda3/envs/tensorflow