Open ramesesz opened 1 year ago
Thanks for pointing this out. The pretrained checkpoint used an old naming scheme. For now, it suffices to copy (not rename) entity_ids.del to entity_map.del, likewise relation_ids.del to relations_map.del, in the dataset folder.
I leave this issue open until we fixed this backward compatibility issue.
I was following the example on the tensor scoring in the readme file
When running
It returns the following error Traceback (most recent call last): File "", line 1, in
File "/home/ramab/workspace/kge/kge/dataset.py", line 494, in entitystrings
map = self.load_map(
File "/home/ramab/workspace/kge/kge/dataset.py", line 315, in load_map
ids = self.load_map(ids_key, as_list=True)
File "/home/ramab/workspace/kge/kge/dataset.py", line 296, in load_map
self.ensure_available(key)
File "/home/ramab/workspace/kge/kge/dataset.py", line 88, in ensure_available
raise IOError(
OSError: File /home/ramab/workspace/kge/data/fb15k-237/entity_map.del for key entity_ids could not be found
I've downloaded all the data through the bash script. Am I missing something?