mys007/ecc

Edge-Conditioned Convolutions on Graphs

ecc's Issues

About torch version

Torch version 0.3 is too old. If I use version 1.0 or above, what changes should I make？
Thanks for your code😄

MNIST Classification

I am trying to replicate the MNIST classification experiment through ECC by following the model configuration reported in your paper. There are some issues that I was not able to solve:
1 - the described network configuration ( C(16)-MP(2,3.4)-C(32)-MP(4,6.8)-C(64)-MP(8,30)-C(128)-D(0.5)-FC(10) ) does not return the proper output dimensions. It seems there is some pooling layer(s) missing. Could you confirm that?
Maybe I am missing something in the following description (network configuration in Section 4.4), when a 4x4 to 1 points map is quoted, how should I get points down-sampling with convolutional layer in ECC?
2 - Could you provide further details about data augmentation and other parameters settings for the same MNIST experiment?

Different point number in Urban Sydney.

Hi, it seems that you did not sample points in Urban Sydney Dataset to ensure they have the same point number.

Frequent Error

Config:

python 3.6.4
torch 1.2.0

This error is frequently triggered stopping the training.

Traceback (most recent call last):
File "learning/main.py", line 607, in
main()
File "learning/main.py", line 455, in main
train_metrics, _ = train()
File "learning/main.py", line 296, in train
outputs = model.ecc(embeddings[0], clouds_data[4:6])
File "/home/thomas/.pyenv/versions/spg3.6.4/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "/home/thomas/HELIX/superpoint-graph-job/superpointgraph2/learning/../learning/graphnet.py", line 145, in forward
input = module(input)
File "/home/thomas/.pyenv/versions/spg3.6.4/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "/home/thomas/HELIX/superpoint-graph-job/superpointgraph2/learning/../learning/modules.py", line 88, in forward
input = ecc.GraphConvFunction(nc, nc, idxn, idxe, degs, degs_gpu, self._edge_mem_limit)(hx, weights)
File "/home/thomas/HELIX/superpoint-graph-job/superpointgraph2/learning/../learning/ecc/GraphConvModule.py", line 67, in forward
cuda_kernels.conv_aggregate_fw(output.narrow(0,startd,numd), products.view(-1,self._out_channels), self._degs_gpu.narrow(0,startd,numd))
File "/home/thomas/HELIX/superpoint-graph-job/superpointgraph2/learning/../learning/ecc/cuda_kernels.py", line 123, in conv_aggregate_fw
csdegs = torch.cumsum(degs,0)
RuntimeError: scan failed to synchronize: an illegal memory access was encountered

Traceback (most recent call last):
File "cupy/cuda/driver.pyx", line 193, in cupy.cuda.driver.moduleUnload
File "cupy/cuda/driver.pyx", line 82, in cupy.cuda.driver.check_status
TypeError: 'NoneType' object is not callable
Exception ignored in: 'cupy.cuda.function.Module.dealloc'
Traceback (most recent call last):
File "cupy/cuda/driver.pyx", line 193, in cupy.cuda.driver.moduleUnload
File "cupy/cuda/driver.pyx", line 82, in cupy.cuda.driver.check_status
TypeError: 'NoneT

cuda_kernels help

Hey,

I am working deeply on your code.
I would like to ask you a favor, and if you could please help me to understand the cuda kernels.
My email adress is [email protected]

I have benchmark your code vs pytorch geometric own implementation and I would say yours is approximately 3 times faster to train.

Best,

pytorch_scatter could maybe be faster for features aggregation

https://github.com/rusty1s/pytorch_scatter

Backpropagation of graph convolution

Hi,
I would like to ask if it is possible to you to explain the backpropagation step of the graph convolution. I would like to know if you can give the equations and their correspondence to the code. I am trying to understand how is the derivative calculated, but I am not able to do it.

Sorry if it is a silly question..

Generalized Graphs

Hi. Great paper and great work. I installed pytorch -0.3 in a conda environment and installed dependencies. The code runs successfully.

I was wondering when the code for generalized graph classification shall be released?

Issues executing examples. CUDA_ERROR_ILLEGAL_ADDRESS and torch.bmm received an invalid combination of arguments

Hi,

I have some issues executing your code. First, I tried to execute your example with modelnet 10 using the command provided. It seemed to work but an advanced epoch the code crash with this error:

Traceback (most recent call last):
  File "main.py", line 315, in <module>
    main()
  File "main.py", line 217, in main
    acc_train, loss, t_loader, t_trainer = train(epoch)
  File "main.py", line 155, in train
    loss_meter.add(loss.data[0])
RuntimeError: cuda runtime error (77) : an illegal memory access was encountered at /pytorch/torch/lib/THC/generic/THCStorage.c:32

Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Exception ignored in: 'cupy.cuda.function.Module.__dealloc__'
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Exception ignored in: 'cupy.cuda.function.Module.__dealloc__'
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Exception ignored in: 'cupy.cuda.function.Module.__dealloc__'
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Exception ignored in: 'cupy.cuda.function.Module.__dealloc__'
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
=

I executed the code several times and the error appears randomly, it is not always in the same epoch, also it is not appearing in the same part of the code, here you can see an other example of the error:

File "main.py", line 315, in <module>
    main()
  File "main.py", line 217, in main
    acc_train, loss, t_loader, t_trainer = train(epoch)
  File "main.py", line 152, in train
    loss.backward()
  File "/projects/env/ecc/lib/python3.6/site-packages/torch/autograd/variable.py", line 167, in backward
    torch.autograd.backward(self, gradient, retain_graph, create_graph, retain_variables)
  File "/projects/env/ecc/lib/python3.6/site-packages/torch/autograd/__init__.py", line 99, in backward
    variables, grad_variables, retain_graph)
RuntimeError: cublas runtime error : an internal operation failed at /pytorch/torch/lib/THC/THCBlas.cu:247

Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Exception ignored in: 'cupy.cuda.function.Module.__dealloc__'
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Exception ignored in: 'cupy.cuda.function.Module.__dealloc__'
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Exception ignored in: 'cupy.cuda.function.Module.__dealloc__'
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered
Exception ignored in: 'cupy.cuda.function.Module.__dealloc__'
Traceback (most recent call last):
  File "cupy/cuda/driver.pyx", line 159, in cupy.cuda.driver.moduleUnload
  File "cupy/cuda/driver.pyx", line 75, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered

I tried different versions of pytorch: 0.2 0.3 0.4. The three versions was installed using pip, and also I tried to execute the code with a compiled from source version (0.2) the same error appears. I am using a machine with: 60gb of ram, Intel Xeon and a titan X with 12gb of ram. Moreover I tried to use different versions of open3d: 0.2.0 and 0.3.0. Finally I modified your sample command and I add edge_mem_limit in order to limit the memory used on the gpu without success.

Also I tested the code using the Sydney Urban Objects example, but in this case, this error is appearing at the begging of the execution:

File "main.py", line 315, in <module>
    main()
  File "main.py", line 217, in main
    acc_train, loss, t_loader, t_trainer = train(epoch)
  File "main.py", line 148, in train
    outputs = model(inputs)
  File "/project/env/ecc/lib/python3.6/site-packages/torch/nn/modules/module.py", line 224, in __call__
    result = self.forward(*input, **kwargs)
  File "/project/code/ecc/models.py", line 103, in forward
    input = module(input)
  File "/project/env/ecc/lib/python3.6/site-packages/torch/nn/modules/module.py", line 224, in __call__
    result = self.forward(*input, **kwargs)
  File "/project/code/ecc/ecc/GraphConvModule.py", line 171, in forward
    return GraphConvFunction(self._in_channels, self._out_channels, idxn, idxe, degs, degs_gpu, self._edge_mem_limit)(input, weights)
  File "/project/code/ecc/ecc/GraphConvModule.py", line 63, in forward
    self._multiply(sel_input, sel_weights, products, lambda a: a.unsqueeze(1))
  File "/project/code/ecc/ecc/GraphConvModule.py", line 36, in _multiply
    torch.bmm(f_a(a) if f_a else a, f_b(b) if f_b else b, out=out)
TypeError: torch.bmm received an invalid combination of arguments - got (torch.DoubleTensor, torch.FloatTensor, out=torch.DoubleTensor), but expected (torch.DoubleTensor source, torch.DoubleTensor mat2, *, torch.DoubleTensor out)

Please can you give me some hint in order to solve the issues?

Thanks,