Fix reconstruction error discussed in #15 #16
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
rom1504
reviewed
Apr 30, 2022
| @@ -292,7 +292,8 @@ def index_embeddings( | |||
| metric_type = "l2", | |||
| max_index_memory_usage = max_index_memory_usage, | |||
| current_memory_available = current_memory_available, | |||
| should_be_memory_mappable = True, | |||
| make_direct_map = True | |||
| should_be_memory_mappable = False, | |||
There was a problem hiding this comment.
oh you can actually keep the memory mapping, it will apply to everything except for the direct map
There was a problem hiding this comment.
I was getting the same error when I did this
There was a problem hiding this comment.
Can you send the full stack trace ? I don't understand
There was a problem hiding this comment.
Hey @rom1504 here is the full stack trace:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
[<ipython-input-3-7b2653026171>](https://localhost:8080/#) in <module>()
32 knn_extra_neighbors = 100, # num extra neighbors to fetch
33 max_index_memory_usage = '100m',
---> 34 current_memory_available = '1G'
35 )
36
11 frames
[/usr/local/lib/python3.7/dist-packages/faiss/swigfaiss.py](https://localhost:8080/#) in reconstruct_n(self, i0, ni, recons)
1997 :param recons: reconstucted vector (size ni * d)
1998 """
-> 1999 return _swigfaiss.Index_reconstruct_n(self, i0, ni, recons)
2000
2001 def search_and_reconstruct(self, n, x, k, distances, labels, recons):
RuntimeError: Error in virtual void faiss::Index::reconstruct(faiss::Index::idx_t, float*) const at /project/faiss/faiss/Index.cpp:48: reconstruct not implemented for this type of index
You can use this colab to reproduce: https://colab.research.google.com/drive/1nvAxBGHnjrNFmgBm8Qu9ZRnmvwQyCFLI?usp=sharing
There was a problem hiding this comment.
Ok i found the problem. You installed faiss-gpu (first line of the colab). Don't do that, use faiss-cpu instead.
Then you can revert this PR
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR fixes the issue with reconstruction of the faiss index. One caveat is that we can no longer do memmapping to reduce RAM overhead. Maybe this will be fixed in faiss soon, but for now memory will be an issue for extremely large indices.