abdulfatir
commented
3 weeks ago Hi @RichardShea! I am not sure if using the same setup as the climate dataset is directly applicable on a new dataset. Maybe try adding print statements to debug which dtype is incorrect?
Hi,
When trying to run a new dataset, I match the datatype exactly as the climate datatype. The new dataset are timestamps generated from a Hawkes process. Below is the error.
Thank you,
-Richard
_Traceback (most recent call last): File "/content/train_ts.py", line 251, in
main()
File "/content/train_ts.py", line 168, in main
train_batch = next(train_gen)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py", line 630, in next
data = self._next_data()
File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py", line 1344, in _next_data
return self._process_data(data)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py", line 1370, in _process_data
data.reraise()
File "/usr/local/lib/python3.10/dist-packages/torch/_utils.py", line 706, in reraise
raise exception
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/worker.py", line 309, in _worker_loop
data = fetcher.fetch(index) # type: ignore[possibly-undefined]
File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/fetch.py", line 55, in fetch
return self.collate_fn(data)
File "/content/ncdssm/datasets/climate.py", line 140, in collate_fn
comb_past_target[i, pastindices] = tgt
RuntimeError: Index put requires the source and destination dtypes match, got Double for the destination and Float for the source.