AttributeError: 'NNConv' object has no attribute '__user_args__'

[Chaunceyw001]

Error with pytorch1.5.0, cuda10.2 in Ubuntu20

1. error reported from "Tiling-Shape.py"

File "./Tiling-Shape.py", line 86, in
tiling_a_region()
File "./Tiling-Shape.py", line 59, in tiling_a_region
result_brick_layout, score = solver.solve(result_brick_layout)
File "/home/Desktop/clone/TilinGNN/solver/ml_solver/ml_solver.py", line 60, in solve
output_solution, score, predict_order = algorithms.solve_by_probablistic_greedy(self, brick_layout)
File "/home/Desktop/clone/TilinGNN/util/algorithms.py", line 31, in solve_by_probablistic_greedy
prob = ml_solver.predict(temp_layout)
File "/home/Desktop/clone/TilinGNN/solver/ml_solver/ml_solver.py", line 43, in predict
col_e_features=collide_edge_features)
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/home/Desktop/clone/TilinGNN/graph_networks/networks/TilinGNN.py", line 62, in forward
brch_1_feature, *_ = conv_layer(brch_1_feature, adj_e_index, adj_e_features)
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/home/Desktop/clone/TilinGNN/graph_networks/layers/edge_conv.py", line 25, in forward
x = self.nnConv(x, edge_index, edge_features)
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch_geometric/nn/conv/nn_conv.py", line 81, in forward
return self.propagate(edge_index, x=x, pseudo=pseudo)
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch_geometric/nn/conv/message_passing.py", line 250, in propagate
kwargs = self.collect(edge_index, size, mp_type, kwargs)
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch_geometric/nn/conv/message_passing.py", line 124, in collect
for arg in self.user_args:
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 594, in getattr
type(self).name, name))
AttributeError: 'NNConv' object has no attribute 'user_args'

2. error reported from "Tiling-GUI.py" when press 'S' to solve

Traceback (most recent call last):
File "./Tiling-GUI.py", line 133, in keyPressEvent
self.current_solution_layout = self.solve_Brick_Layout(self.current_brick_layout)
File "./Tiling-GUI.py", line 489, in solve_Brick_Layout
result_brick_layout, score = self.solver.solve(brick_layout)
File "/home/Desktop/clone/TilinGNN/solver/ml_solver/ml_solver.py", line 60, in solve
output_solution, score, predict_order = algorithms.solve_by_probablistic_greedy(self, brick_layout)
File "/home/Desktop/clone/TilinGNN/util/algorithms.py", line 31, in solve_by_probablistic_greedy
prob = ml_solver.predict(temp_layout)
File "/home/Desktop/clone/TilinGNN/solver/ml_solver/ml_solver.py", line 43, in predict
col_e_features=collide_edge_features)
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/home/Desktop/clone/TilinGNN/graph_networks/networks/TilinGNN.py", line 62, in forward
brch_1_feature, *_ = conv_layer(brch_1_feature, adj_e_index, adj_e_features)
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/home/Desktop/clone/TilinGNN/graph_networks/layers/edge_conv.py", line 25, in forward
x = self.nnConv(x, edge_index, edge_features)
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch_geometric/nn/conv/nn_conv.py", line 81, in forward
return self.propagate(edge_index, x=x, pseudo=pseudo)
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch_geometric/nn/conv/message_passing.py", line 250, in propagate
kwargs = self.collect(edge_index, size, mp_type, kwargs)
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch_geometric/nn/conv/message_passing.py", line 124, in collect
for arg in self.user_args:
File "/home/.conda/envs/pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 594, in getattr
type(self).name, name))
AttributeError: 'NNConv' object has no attribute 'user_args'

[xuhaocuhk]

Hi, thank you for raising this issue, but we cannot reproduce this error.
Could you tell us which version of your "Pytorch geometric" package you are using?

[Chaunceyw001]

Hi, thank you for raising this issue, but we cannot reproduce this error.
Could you tell us which version of your "Pytorch geometric" package you are using?

packages in environment at /home/.conda/envs/pytorch:

Name Version Build Channel

_libgcc_mutex 0.1 main
ase 3.19.1 pypi_0 pypi
blas 1.0 mkl
bzip2 1.0.8 h7b6447c_0
ca-certificates 2020.1.1 0
cairo 1.14.12 h8948797_3
certifi 2020.4.5.2 py37_0
chardet 3.0.4 pypi_0 pypi
cudatoolkit 10.2.89 hfd86e86_1
cycler 0.10.0 pypi_0 pypi
decorator 4.4.2 pypi_0 pypi
ffmpeg 4.0 hcdf2ecd_0
fontconfig 2.13.0 h9420a91_0
freeglut 3.0.0 hf484d3e_5
freetype 2.9.1 h8a8886c_1
future 0.18.2 pypi_0 pypi
glib 2.63.1 h3eb4bd4_1
googledrivedownloader 0.4 pypi_0 pypi
graphite2 1.3.13 h23475e2_0
h5py 2.10.0 pypi_0 pypi
harfbuzz 1.8.8 hffaf4a1_0
hdf5 1.10.2 hba1933b_1
icu 58.2 he6710b0_3
idna 2.9 pypi_0 pypi
intel-openmp 2020.1 217
isodate 0.6.0 pypi_0 pypi
jasper 2.0.14 h07fcdf6_1
joblib 0.15.1 pypi_0 pypi
jpeg 9b h024ee3a_2
kiwisolver 1.2.0 pypi_0 pypi
ld_impl_linux-64 2.33.1 h53a641e_7
libedit 3.1.20181209 hc058e9b_0
libffi 3.3 he6710b0_1
libgcc-ng 9.1.0 hdf63c60_0
libgfortran-ng 7.3.0 hdf63c60_0
libglu 9.0.0 hf484d3e_1
libopencv 3.4.2 hb342d67_1
libopus 1.3.1 h7b6447c_0
libpng 1.6.37 hbc83047_0
libstdcxx-ng 9.1.0 hdf63c60_0
libtiff 4.1.0 h2733197_1
libuuid 1.0.3 h1bed415_2
libvpx 1.7.0 h439df22_0
libxcb 1.13 h1bed415_1
libxml2 2.9.10 he19cac6_1
llvmlite 0.33.0 pypi_0 pypi
lz4-c 1.9.2 he6710b0_0
matplotlib 3.2.1 pypi_0 pypi
mkl 2020.1 217
mkl-service 2.3.0 py37he904b0f_0
mkl_fft 1.0.15 py37ha843d7b_0
mkl_random 1.1.1 py37h0573a6f_0
ncurses 6.2 he6710b0_1
networkx 2.4 pypi_0 pypi
ninja 1.9.0 py37hfd86e86_0
numba 0.50.0 pypi_0 pypi
numpy 1.18.1 py37h4f9e942_0
numpy-base 1.18.1 py37hde5b4d6_1
olefile 0.46 py37_0
opencv 3.4.2 py37h6fd60c2_1
openssl 1.1.1g h7b6447c_0
pandas 1.0.4 pypi_0 pypi
pcre 8.43 he6710b0_0
pillow 7.1.2 py37hb39fc2d_0
pip 20.0.2 py37_3
pixman 0.38.0 h7b6447c_0
plyfile 0.7.2 pypi_0 pypi
py-opencv 3.4.2 py37hb342d67_1
pyparsing 2.4.7 pypi_0 pypi
pyqt5 5.15.0 pypi_0 pypi
pyqt5-sip 12.8.0 pypi_0 pypi
python 3.7.7 hcff3b4d_5
python-dateutil 2.8.1 pypi_0 pypi
pytorch 1.5.0 py3.7_cuda10.2.89_cudnn7.6.5_0 pytorch
pytz 2020.1 pypi_0 pypi
rdflib 5.0.0 pypi_0 pypi
readline 8.0 h7b6447c_0
requests 2.23.0 pypi_0 pypi
scikit-learn 0.23.1 pypi_0 pypi
scipy 1.4.1 pypi_0 pypi
setuptools 47.1.1 py37_0
shapely 1.7.0 pypi_0 pypi
six 1.15.0 py_0
sqlite 3.31.1 h62c20be_1
threadpoolctl 2.1.0 pypi_0 pypi
tk 8.6.8 hbc83047_0
torch-cluster 1.5.4 pypi_0 pypi
torch-geometric 1.5.0 pypi_0 pypi
torch-scatter 2.0.4 pypi_0 pypi
torch-sparse 0.6.5 pypi_0 pypi
torch-spline-conv 1.2.0 pypi_0 pypi
torchvision 0.6.0 py37_cu102 pytorch
tqdm 4.46.1 pypi_0 pypi
urllib3 1.25.9 pypi_0 pypi
wheel 0.34.2 py37_0
xz 5.2.5 h7b6447c_0
zlib 1.2.11 h7b6447c_3
zstd 1.4.4 h0b5b093_3

[xuhaocuhk]

This problem is due to the incompatible version of the pytorch and torch geometric package. Our pre-trained models were trained with pytorch 1.2.0, and torch geometric 1.3.2. The loading model failed due to the package update. You may rollback the two packages to an older version and try if it works.
We will also train new models on new packages and release them ASAP.

[xuhaocuhk]

Hi, we just fixed the problem, please pull the code and try again.

Hao

[Chaunceyw001]

Thanks for your fast action. Now it is solved, so I will close this one.