Hello everybody,
I am using DGL inside the following project that I have cloned.
Unfortunately there occurs an error while training the algorithm.
The call of
python3 train_fairGNN.py --seed=42 --epochs=2000 --model=GCN --sens_number=200 --dataset=pokec_z --num-hidden=128 --acc=0.69 --roc=0.76 --alpha=100 --beta=1
leads to the following error message
Using backend: pytorch
Traceback (most recent call last):
File "train_fairGNN.py", line 154, in <module>
model.optimize(G,features,labels,idx_train,sens,idx_sens_train)
File "/home/rolo/Dokumente/RWTH/Sem5/Praktikum/forschungspraktikum/FairGNN/src/models/FairGNN.py", line 53, in optimize
s = self.estimator(g,x)
File "/home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/rolo/Dokumente/RWTH/Sem5/Praktikum/forschungspraktikum/FairGNN/src/models/GCN.py", line 12, in forward
x = self.body(g,x)
File "/home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/rolo/Dokumente/RWTH/Sem5/Praktikum/forschungspraktikum/FairGNN/src/models/GCN.py", line 26, in forward
x = F.relu(self.gc1(g, x))
File "/home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/nn/pytorch/conv/graphconv.py", line 429, in forward
graph.update_all(aggregate_fn, fn.sum(msg='m', out='h'))
File "/home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/heterograph.py", line 4849, in update_all
ndata = core.message_passing(g, message_func, reduce_func, apply_node_func)
File "/home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/core.py", line 322, in message_passing
ndata = invoke_gspmm(g, mfunc, rfunc)
File "/home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/core.py", line 297, in invoke_gspmm
z = op(graph, x)
File "/home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/ops/spmm.py", line 191, in func
return gspmm(g, 'copy_lhs', reduce_op, x, None)
File "/home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/ops/spmm.py", line 77, in gspmm
lhs_data, rhs_data)
File "/home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/backend/pytorch/sparse.py", line 503, in gspmm
return GSpMM.apply(gidx, op, reduce_op, lhs_data, rhs_data)
File "/home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/torch/cuda/amp/autocast_mode.py", line 94, in decorate_fwd
return fwd(*args, **kwargs)
File "/home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/backend/pytorch/sparse.py", line 123, in forward
out, (argX, argY) = _gspmm(gidx, op, reduce_op, X, Y)
File "/home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/sparse.py", line 162, in _gspmm
arg_e_nd)
File "dgl/_ffi/_cython/./function.pxi", line 287, in dgl._ffi._cy3.core.FunctionBase.__call__
File "dgl/_ffi/_cython/./function.pxi", line 232, in dgl._ffi._cy3.core.FuncCall
File "dgl/_ffi/_cython/./base.pxi", line 155, in dgl._ffi._cy3.core.CALL
dgl._ffi.base.DGLError: [14:06:48] /opt/dgl/src/array/cpu/./spmm_blocking_libxsmm.h:267: Failed to generate libxsmm kernel for the SpMM operation!
Stack trace:
[bt] (0) /home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/libdgl.so(dmlc::LogMessageFatal::~LogMessageFatal()+0x4f) [0x7f6e6a15508f]
[bt] (1) /home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/libdgl.so(void dgl::aten::cpu::SpMMRedopCsrOpt<long, float, dgl::aten::cpu::op::CopyLhs<float>, dgl::aten::cpu::op::Add<float> >(dgl::BcastOff const&, dgl::aten::CSRMatrix const&, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray)+0x3d4) [0x7f6e6a324fe4]
[bt] (2) /home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/libdgl.so(void dgl::aten::cpu::SpMMSumCsrLibxsmm<long, float, dgl::aten::cpu::op::CopyLhs<float> >(dgl::BcastOff const&, dgl::aten::CSRMatrix const&, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray)+0x73) [0x7f6e6a325093]
[bt] (3) /home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/libdgl.so(void dgl::aten::cpu::SpMMSumCsr<long, float, dgl::aten::cpu::op::CopyLhs<float> >(dgl::BcastOff const&, dgl::aten::CSRMatrix const&, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray)+0x12f) [0x7f6e6a33ea7f]
[bt] (4) /home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/libdgl.so(void dgl::aten::SpMMCsr<1, long, 32>(std::string const&, std::string const&, dgl::BcastOff const&, dgl::aten::CSRMatrix const&, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray, std::vector<dgl::runtime::NDArray, std::allocator<dgl::runtime::NDArray> >)+0xcd3) [0x7f6e6a34fb93]
[bt] (5) /home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/libdgl.so(dgl::aten::SpMM(std::string const&, std::string const&, std::shared_ptr<dgl::BaseHeteroGraph>, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray, std::vector<dgl::runtime::NDArray, std::allocator<dgl::runtime::NDArray> >)+0x13d5) [0x7f6e6a379655]
[bt] (6) /home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/libdgl.so(+0x467e08) [0x7f6e6a383e08]
[bt] (7) /home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/libdgl.so(+0x4683a1) [0x7f6e6a3843a1]
[bt] (8) /home/rolo/miniconda3/envs/forschungspraktikumenv/lib/python3.7/site-packages/dgl/libdgl.so(DGLFuncCall+0x48) [0x7f6e6a926278]
Namespace(acc=0.69, alpha=100.0, attn_drop=0.0, beta=1.0, cuda=False, dataset='pokec_z', dropout=0.5, epochs=2000, fastmode=False, hidden=128, label_number=500, lr=0.001, model='GCN', negative_slope=0.2, no_cuda=False, num_heads=1, num_hidden=128, num_layers=1, num_out_heads=1, residual=False, roc=0.76, seed=42, sens_number=200, weight_decay=1e-05)
pokec_z
region_job
Loading region_job dataset from ../dataset/pokec/
2566
I am using pytorch in it’s CPUonly-version in an own conda environment. My PC does not have a GPU.
Here the packages that are installed in my conda environment:
# Name Version Build Channel
_libgcc_mutex 0.1 main
_openmp_mutex 4.5 1_gnu
absl-py 0.13.0 py37h06a4308_0
aif360 0.4.0 pyhd8ed1ab_1 conda-forge
aiohttp 3.8.1 py37h7f8727e_0
aiosignal 1.2.0 pyhd3eb1b0_0
argcomplete 1.12.3 pyhd3eb1b0_0
argon2-cffi 20.1.0 py37h27cfd23_1
ase 3.22.0 pyhd8ed1ab_1 conda-forge
astor 0.8.1 py37h06a4308_0
async-timeout 4.0.1 pyhd3eb1b0_0
async_generator 1.10 py37h28b3542_0
asynctest 0.13.0 py_0
attrs 21.2.0 pyhd3eb1b0_0
backcall 0.2.0 py_0 anaconda
blas 1.0 mkl
bleach 4.0.0 pyhd3eb1b0_0
blosc 1.21.0 h8c45485_0
bokeh 2.4.2 py_0 bokeh
boto3 1.18.21 pyhd3eb1b0_0
botocore 1.21.41 pyhd3eb1b0_1
brotli 1.0.9 he6710b0_2
brotlipy 0.7.0 py37h27cfd23_1003
brunsli 0.1 h2531618_0
bzip2 1.0.8 h7b6447c_0
c-ares 1.17.1 h27cfd23_0
ca-certificates 2021.10.26 h06a4308_2
cached-property 1.5.2 py_0 anaconda
cachetools 4.2.2 pyhd3eb1b0_0
captum 0.4.1 0 pytorch
certifi 2021.10.8 py37h06a4308_0
cffi 1.14.6 py37h400218f_0
cfitsio 3.470 hf0d0db6_6
chardet 3.0.4 py37h06a4308_1003
charls 2.2.0 h2531618_0
charset-normalizer 2.0.4 pyhd3eb1b0_0
click 7.1.2 py_0 anaconda
cloudpickle 2.0.0 pyhd3eb1b0_0
colorama 0.4.4 pyhd3eb1b0_0
colorcet 2.0.2 py_0 anaconda
cpuonly 2.0 0 pytorch
cryptography 35.0.0 py37hd23ed53_0
cycler 0.11.0 pyhd3eb1b0_0
cytoolz 0.11.0 py37h7b6447c_0
dask 2021.10.0 pyhd3eb1b0_0
dask-core 2021.10.0 pyhd3eb1b0_0
dataclasses 0.8 pyh6d0b6a4_7
datashader 0.11.1 py_0 anaconda
datashape 0.5.4 py_1 conda-forge
debugpy 1.5.1 py37h295c915_0
decorator 5.1.0 pyhd3eb1b0_0
deeprobust 0.2.2 pyhd8ed1ab_0 conda-forge
defusedxml 0.7.1 pyhd3eb1b0_0
dgl 0.7.2 py37_0 dglteam
distributed 2021.10.0 py37h06a4308_0
entrypoints 0.3 py37_0
ffmpeg 4.2.2 h20bf706_0
flask 2.0.2 pyhd3eb1b0_0
freetype 2.11.0 h70c0345_0
frozenlist 1.2.0 py37h7f8727e_0
fsspec 2021.10.1 pyhd3eb1b0_0
future 0.18.2 py37h89c1867_4 conda-forge
gast 0.5.3 pyhd3eb1b0_0
gensim 3.8.3 py37h2531618_2
giflib 5.2.1 h7b6447c_0
gmp 6.2.1 h2531618_2
gnutls 3.6.15 he1e5248_0
google-api-core 1.25.1 pyhd3eb1b0_0
google-auth 1.33.0 pyhd3eb1b0_0
google-cloud-core 1.7.1 pyhd3eb1b0_0
google-cloud-storage 1.41.0 pyhd3eb1b0_0
google-crc32c 1.1.2 py37h27cfd23_0
google-pasta 0.2.0 pyhd3eb1b0_0
google-resumable-media 1.3.1 pyhd3eb1b0_1
googleapis-common-protos 1.53.0 py37h06a4308_0
googledrivedownloader 0.4 pyhd3deb0d_1 conda-forge
grpcio 1.42.0 py37hce63b2e_0
h5py 2.10.0 py37hd6299e0_1 anaconda
hdf5 1.10.6 hb1b8bf9_0
heapdict 1.0.1 py_0 anaconda
holoviews 1.14.6 pyhd3eb1b0_1
html5lib 1.1 pyhd3eb1b0_0
icu 58.2 he6710b0_3
idna 2.10 py_0 anaconda
imagecodecs 2021.8.26 py37h4cda21f_0
imageio 2.9.0 pyhd3eb1b0_0
imgcat 0.5.0 pypi_0 pypi
importlib-metadata 4.8.1 py37h06a4308_0
importlib_metadata 4.8.1 hd3eb1b0_0
iniconfig 1.1.1 pyhd3eb1b0_0
intel-openmp 2021.4.0 h06a4308_3561
ipdb 0.13.9 pyhd8ed1ab_0 conda-forge
ipykernel 6.4.1 py37h06a4308_1
ipython 7.29.0 py37hb070fc8_0
ipython_genutils 0.2.0 pyhd3eb1b0_1
isodate 0.6.0 py_1 conda-forge
itsdangerous 2.0.1 pyhd3eb1b0_0
jedi 0.18.0 py37h06a4308_1
jinja2 3.0.2 pyhd3eb1b0_0
jmespath 0.10.0 pyhd3eb1b0_0
joblib 1.1.0 pyhd3eb1b0_0
jpeg 9d h7f8727e_0
jsonschema 3.2.0 pyhd3eb1b0_2
jupyter_client 7.0.6 pyhd3eb1b0_0
jupyter_core 4.9.1 py37h06a4308_0
jupyterlab_pygments 0.1.2 py_0
jxrlib 1.1 h7b6447c_2
keepalive 0.5 pyhd8ed1ab_6 conda-forge
keras-applications 1.0.8 py_1
keras-preprocessing 1.1.2 pyhd3eb1b0_0
kiwisolver 1.3.1 py37h2531618_0
krb5 1.19.2 hac12032_0
lame 3.100 h7b6447c_0
lcms2 2.12 h3be6417_0
ld_impl_linux-64 2.35.1 h7274673_9
lerc 3.0 h295c915_0
libaec 1.0.4 he6710b0_1
libcrc32c 1.1.1 he6710b0_2
libcurl 7.78.0 h0b77cf5_0
libdeflate 1.8 h7f8727e_5
libedit 3.1.20210910 h7f8727e_0
libev 4.33 h7f8727e_1
libffi 3.3 he6710b0_2
libgcc-ng 9.3.0 h5101ec6_17
libgfortran-ng 7.5.0 ha8ba4b0_17
libgfortran4 7.5.0 ha8ba4b0_17
libgomp 9.3.0 h5101ec6_17
libidn2 2.3.2 h7f8727e_0
libnghttp2 1.46.0 hce63b2e_0
libopus 1.3.1 h7b6447c_0
libpng 1.6.37 hbc83047_0
libprotobuf 3.17.2 h4ff587b_1
libsodium 1.0.18 h7b6447c_0
libssh2 1.9.0 h1ba5d50_1
libstdcxx-ng 9.3.0 hd4cf53a_17
libtasn1 4.16.0 h27cfd23_0
libtiff 4.2.0 h85742a9_0
libunistring 0.9.10 h27cfd23_0
libuv 1.40.0 h7b6447c_0
libvpx 1.7.0 h439df22_0
libwebp 1.2.0 h89dd481_0
libwebp-base 1.2.0 h27cfd23_0
libzopfli 1.0.3 he6710b0_0
llvmlite 0.37.0 py37he1b5a44_0 numba
locket 0.2.1 py37h06a4308_1
lz4-c 1.9.3 h295c915_1
markdown 3.3.2 py37_0 anaconda
markupsafe 2.0.1 py37h27cfd23_0
matplotlib 3.2.2 1 conda-forge
matplotlib-base 3.2.2 py37hef1b27d_0
matplotlib-inline 0.1.2 pyhd3eb1b0_2
memory_profiler 0.58.0 pyhd3eb1b0_0
metis 5.1.0 hf484d3e_4 anaconda
mistune 0.8.4 py37h14c3975_1001
mkl 2019.4 243
mkl-service 2.3.0 py37he8ac12f_0
mkl_fft 1.3.0 py37h54f3939_0
mkl_random 1.1.0 py37hd6b4f25_0
more-itertools 8.12.0 pyhd3eb1b0_0
msgpack-python 1.0.0 py37hfd86e86_1 anaconda
multidict 5.1.0 py37h27cfd23_2
multipledispatch 0.6.0 py37_0
nb_conda 2.2.1 py37h06a4308_1
nb_conda_kernels 2.3.1 py37h06a4308_0
nbclient 0.5.3 pyhd3eb1b0_0
nbconvert 6.1.0 py37h06a4308_0
nbformat 5.1.3 pyhd3eb1b0_0
ncurses 6.3 h7f8727e_2
nest-asyncio 1.5.1 pyhd3eb1b0_0
nettle 3.7.3 hbbd107a_1
networkx 2.6.3 pyhd3eb1b0_0
notebook 6.4.6 py37h06a4308_0
numba 0.54.1 py37h51133e4_0
numpy 1.19.1 py37hbc911f0_0 anaconda
numpy-base 1.19.1 py37hfa32c7d_0
olefile 0.46 py37_0
openh264 2.1.0 hd408876_0
openjpeg 2.4.0 h3ad879b_0
openssl 1.1.1l h7f8727e_0
packaging 21.3 pyhd3eb1b0_0
pandas 1.1.3 py37he6710b0_0 anaconda
pandocfilters 1.4.3 py37h06a4308_1
panel 0.10.2 py_0 pyviz
param 1.9.3 py_0 anaconda
parso 0.8.2 pyhd3eb1b0_0
partd 1.2.0 pyhd3eb1b0_0
pexpect 4.8.0 pyhd3eb1b0_3
pickleshare 0.7.5 pyhd3eb1b0_1003
pillow 8.4.0 py37h5aabda8_0
pip 21.2.2 py37h06a4308_0
plotly 5.4.0 py_0 plotly
pluggy 0.13.1 py37h06a4308_0
prometheus_client 0.12.0 pyhd3eb1b0_0
prompt-toolkit 3.0.22 pyha770c72_0 conda-forge
prompt_toolkit 3.0.22 hd8ed1ab_0 conda-forge
protobuf 3.17.2 py37h295c915_0
psutil 5.8.0 py37h27cfd23_1
ptyprocess 0.7.0 pyhd3eb1b0_2
py 1.10.0 pyhd3eb1b0_0
pyasn1 0.4.8 pyhd3eb1b0_0
pyasn1-modules 0.2.8 py_0
pycparser 2.21 pyhd3eb1b0_0
pyct 0.4.8 py37_0
pyg 2.0.2 py37_torch_1.10.0_cpu pyg
pygments 2.10.0 pyhd3eb1b0_0
pyopenssl 21.0.0 pyhd3eb1b0_1
pyparsing 3.0.4 pyhd3eb1b0_0
pyrsistent 0.18.0 py37heee7806_0
pysocks 1.7.1 py37_1
pytest 6.2.4 py37h06a4308_2
python 3.7.11 h12debd9_0
python-dateutil 2.8.2 pyhd3eb1b0_0
python-louvain 0.15 pyhd3eb1b0_0
python_abi 3.7 2_cp37m conda-forge
pytorch 1.10.0 py3.7_cpu_0 pytorch
pytorch-cluster 1.5.9 py37_torch_1.10.0_cpu pyg
pytorch-mutex 1.0 cpu pytorch
pytorch-scatter 2.0.9 py37_torch_1.10.0_cpu pyg
pytorch-sparse 0.6.12 py37_torch_1.10.0_cpu pyg
pytorch-spline-conv 1.2.1 py37_torch_1.10.0_cpu pyg
pytz 2021.3 pyhd3eb1b0_0
pyviz_comms 2.0.2 pyhd3eb1b0_0
pywavelets 1.1.1 py37h7b6447c_2
pyyaml 6.0 py37h7f8727e_1
pyzmq 22.2.1 py37h295c915_1
ranger 0.10 pypi_0 pypi
ranger-fm 1.9.3 pyh9f0ad1d_0 conda-forge
rdflib 6.0.2 py37h89c1867_0 conda-forge
readline 8.1 h27cfd23_0
requests 2.24.0 py_0 anaconda
retrying 1.3.3 py_2 conda-forge
rsa 4.7.2 pyhd3eb1b0_1
s3transfer 0.5.0 pyhd3eb1b0_0
scikit-image 0.18.3 py37h51133e4_0
scikit-learn 1.0.1 py37h51133e4_0
scipy 1.5.2 py37h0b6359f_0
seaborn 0.11.0 py_0 anaconda
send2trash 1.8.0 pyhd3eb1b0_1
setuptools 58.0.4 py37h06a4308_0
shap 0.39.0 py37h51133e4_0
six 1.16.0 pyhd3eb1b0_0
slicer 0.0.7 pyhd3eb1b0_0
smart_open 5.1.0 pyhd3eb1b0_0
snappy 1.1.8 he6710b0_0
sortedcontainers 2.4.0 pyhd3eb1b0_0
sparqlwrapper 1.8.5 py37h89c1867_1006 conda-forge
sqlite 3.36.0 hc218d9a_0
tbb 2021.4.0 hd09550d_0
tblib 1.7.0 pyhd3eb1b0_0
tempeh 0.1.12 pyhd8ed1ab_0 conda-forge
tenacity 8.0.1 py37h06a4308_0
tensorboard 1.14.0 py37hf484d3e_0
tensorboardx 2.2 pyhd3eb1b0_0
tensorflow 1.14.0 h4531e10_0 conda-forge
tensorflow-base 1.14.0 py37h4531e10_0 conda-forge
tensorflow-estimator 1.14.0 py_0
termcolor 1.1.0 py37h06a4308_1
terminado 0.9.4 py37h06a4308_0
testpath 0.5.0 pyhd3eb1b0_0
texttable 1.6.4 pyhd3eb1b0_0
threadpoolctl 2.2.0 pyh0d69192_0
tifffile 2021.11.2 pyhd8ed1ab_0 conda-forge
tk 8.6.11 h1ccaba5_0
toml 0.10.2 pyhd3eb1b0_0
toolz 0.11.2 pyhd3eb1b0_0
torchaudio 0.10.0 py37_cpu [cpuonly] pytorch
torchsummary 1.5.1 pypi_0 pypi
torchvision 0.11.1 py37_cpu [cpuonly] pytorch
tornado 6.1 py37h27cfd23_0
tqdm 4.62.3 pyhd8ed1ab_0 conda-forge
traitlets 5.0.5 py_0 anaconda
typing-extensions 3.10.0.2 hd3eb1b0_0
typing_extensions 3.10.0.2 pyh06a4308_0
urllib3 1.25.11 py_0
wcwidth 0.2.5 pyhd3eb1b0_0
webencodings 0.5.1 py37_1
werkzeug 2.0.2 pyhd3eb1b0_0
wheel 0.37.0 pyhd3eb1b0_1
wrapt 1.13.3 py37h7f8727e_1
x264 1!157.20191217 h7b6447c_0
xarray 0.19.0 pyhd3eb1b0_1
xz 5.2.5 h7b6447c_0
yacs 0.1.6 pyhd3eb1b0_1
yaml 0.2.5 h7b6447c_0
yarl 1.5.1 py37h7b6447c_0
zeromq 4.3.4 h2531618_0
zfp 0.5.5 h2531618_6
zict 2.0.0 pyhd3eb1b0_0
zipp 3.6.0 pyhd3eb1b0_0
zlib 1.2.11 h7b6447c_3
zstd 1.4.9 haebb681_0
Can anybody help me with this?
Thank you in advance,
Maggi