20171130 / equivariant-nn-zoo Goto Github PK
View Code? Open in Web Editor NEWA library for building equivariant neural networks and a zoo of implementations & examples.
License: MIT License
A library for building equivariant neural networks and a zoo of implementations & examples.
License: MIT License
Thank you so much for this great repository.
I was wondering if you could help me with figuring out how to prevent this error? I think this is happening because the object passed to collator from the dataloader is not a list and only the attributes are left when getting the next(iter(dataset)). I tried to unravel the batch object but I observed that the tensors of coordinates, for example, are all concatenated along the same dimension across all samples. Is this intended since we are relying on the edge_index? Also, I tried to calculate edge_index before passing the dataset but that did not help (is edge_index internally calculated if omitted from preparing the HDF5 dataset?)
Here is my traceback on the error I am facing:
Traceback (most recent call last):
File "train.py", line 311, in
launch_mp()
File "train.py", line 295, in launch_mp
main(0)
File "train.py", line 278, in main
train_regression(e3_config, FLAGS)
File "train.py", line 72, in train_regression
trainer.train()
File "/content/drive/MyDrive/Colab_Notebooks/Equivariant-NN-Zoo/e3_layers/run/trainer.py", line 329, in train
self.epoch_step()
File "/content/drive/MyDrive/Colab_Notebooks/Equivariant-NN-Zoo-master/e3_layers/run/trainer.py", line 468, in epoch_step
batch = next(iterable)
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 628, in next
data = self._next_data()
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 1333, in _next_data
return self._process_data(data)
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 1359, in _process_data
data.reraise()
File "/usr/local/lib/python3.8/dist-packages/torch/_utils.py", line 543, in reraise
raise exception
AssertionError: Caught AssertionError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop
data = fetcher.fetch(index)
File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/fetch.py", line 61, in fetch
return self.collate_fn(data)
File "/content/drive/MyDrive/Colab_Notebooks/Equivariant-NN-Zoo-master/e3_layers/data/dataloader.py", line 31, in call
return self.collate(batch)
File "/content/drive/MyDrive/Colab_Notebooks/Equivariant-NN-Zoo/e3_layers/data/dataloader.py", line 26, in collate
out = Batch.from_data_list(batch, attrs=batch[0].attrs)
File "/content/drive/MyDrive/Colab_Notebooks/Equivariant-NN-Zoo/e3_layers/data/batch.py", line 58, in from_data_list
assert node_key is not None, 'Unable to infer the amount of nodes.'
AssertionError: Unable to infer the amount of nodes.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.