-
Just FWIW I'm not seeing dithering, except oddly the "software frame buffer" is dithered (when working that is: #427)
I realize shaders can implement dither, and it would be bad to dither on top of…
-
Question on parameter ranges that I know you have hinted at in other issues, but as far as I can tell haven't directly addressed. I am also referencing the following link:
https://github.com/nmsli…
lkoll updated
6 years ago
-
Hi,
I'm not sure how this fits with all the methods you guys have implemented but I was curious if you support methods based on Product Quantization?
[Product quantization for nearest neighbor s…
-
I noticed two issues with speed. I am working with a dataset with n=14k and dimensionality 50.
1. The gradient descent iterations become slower and slower as they progress. This is most pronounced …
-
Original API separate different steps of the creation of an index (setup, data loading, index loading OR index creation). There is also function to change parameter of search (setQueryTimeParams). Wou…
-
Trying to convert a .vec file to .magnitude along with an annoy approximate index falls into an infinte loop whereby it continually prints `100.0%`.
Using the repo's `test/models/fasttext.vec` as a…
-
When add the new element, we need to update the endpoints to the closest elements from friends list.
(line number 11 of algorithm 1 on page 6 in the paper - "Efficient and robust approximate nearest …
-
I ran the test_ann_class.m code in the ann_wrapper, it says done testing. But when I ran the robustpn_test code, it says "Warn: ann error: ann:open Make sure you have ANN class installed: ". Why is th…
-
[Faiss](https://github.com/facebookresearch/faiss) implemented k-means clustering in PQ space.
According to https://github.com/facebookresearch/faiss/wiki/Low-level-benchmarks, it shows very compe…
-
Quite a boatload of errors considering I copied the install instruction from sklearn site itself.
> Ernests-MacBook-Pro:~ ernest$ pip3 install -U numpy scipy scikit-learn
> Requirement already up-to…