Closed jyw777 closed 5 years ago
It seems to be an issue from the SparseConvNet code.
It is probably because I have downloaded Sparseconv repo before and now I download the MASC which also contain Sparseconv repo. When I remove the Sparseconv repo I downloaded before, I can run the code.
Thank you !
Hi @art-programmer , @chenliu-wustl, Thanks for your codes.
When I trained the model, I got the output like this: keyname=instance_normal_augment_2 task=train started the number of images val 20 the number of images train 1201 the number of images 1201
But after that, I got: Traceback (most recent call last): File "train.py", line 390, in
main(args)
File "train.py", line 91, in main
augmented_coords, augmented_colors, augmentedinstances, = augmentation_model(coords[batch_index], faces[batch_index], colors[batch_index], instances[batch_index])
File "/orion/u/jiayun/env/anaconda3/envs/sp/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, *kwargs)
File "/orion/u/jiayun/downloads/MASC/models/instance.py", line 199, in forward
voxel = self.input_layer((all_coords, all_values))
File "/orion/u/jiayun/env/anaconda3/envs/sp/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(input, kwargs)
File "/orion/u/jiayun/downloads/MASC/src/sparseconvnet/sparseconvnet/ioLayers.py", line 49, in forward
self.dimension),
File "/orion/u/jiayun/downloads/MASC/src/sparseconvnet/sparseconvnet/metadata.py", line 17, in Metadata
return getattr(sparseconvnet.SCN, 'Metadata_%d'%dim)()
AttributeError: module 'sparseconvnet.SCN' has no attribute 'Metadata_3'**
Do you have any idea about that? Thanks.