Error during initialization

[skarlosdeus]

Hi all,

thanks for this great tool.
I am using SEAL that exploits DGCNN, and I am getting the next error during the initialization of your tool:

pytorch_DGCNN/main.py:175: RuntimeWarning: invalid value encountered in double_scalars
avg_loss = np.sum(total_loss, 0) / n_samples
Traceback (most recent call last):
File "Main.py", line 241, in
train_graphs, classifier, train_idxes, optimizer=optimizer, bsize=args.batch_size
File "/home/scarlos/Documents/git/SEAL/Python/../../pytorch_DGCNN/main.py", line 176, in loop_dataset
all_scores = torch.cat(all_scores).cpu().numpy()
NotImplementedError: There were no tensor arguments to this function (e.g., you passed an empty list of Tensors), but no fallback function is registered for schema aten::_cat. This usually means that this function requires a non-empty list of Tensors, or that you (the operator writer) forgot to register a fallback function. Available functions are [CPU, CUDA, QuantizedCPU, BackendSelect, Named, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, UNKNOWN_TENSOR_TYPE_ID, AutogradMLC, AutogradHPU, AutogradNestedTensor, AutogradPrivateUse1, AutogradPrivateUse2, AutogradPrivateUse3, Tracer, Autocast, Batched, VmapMode].

Any idea?
Thanks.

[skarlosdeus]

And this message when the proposed versions were used (Python 3.8.1 and Pytorch 1.4.0):

main.py:175: RuntimeWarning: invalid value encountered in double_scalars
avg_loss = np.sum(total_loss, 0) / n_samples
Traceback (most recent call last):
File "Main.py", line 240, in
avg_loss = loop_dataset(
File "/home/scarlos/Documents/git/SEAL/Python/../../pytorch_DGCNN/main.py", line 176, in loop_dataset
all_scores = torch.cat(all_scores).cpu().numpy()
RuntimeError: There were no tensor arguments to this function (e.g., you passed an empty list of Tensors), but no fallback function is registered for schema aten::_cat. This usually means that this function requires a non-empty list of Tensors. Available functions are [CUDATensorId, CPUTensorId, VariableTensorId]

[muhanzhang]

Hi! Can you "import pdb" and add "pdb.set_trace()" before the line of "all_scores = torch.cat(all_scores).cpu().numpy()"? Then you can print the values of "all_scores" and see if they are empty, thus debugging thereby.