-
I found [LazySelect](https://dl.acm.org/doi/pdf/10.5555/1882757.1882769) (section 12.2.1). Here is a [numpy implementation](https://github.com/upupming/quick-select/blob/master/src/lazy_selector.py). …
-
I'm starting this thread to begin discussions about the upcoming weights sprint. The current experimental implementation is in the [`geographs` branch, the `weights/experimental` module](https://githu…
-
Currently, the logic for selecting matching records is working in two ways:
- 1:1 matching using `select_greedy` or `select_n_to_m`
- Selection of pairs above a certain treshold using `select_tres…
-
Once you implement a db that saves the URL and caption, you can easily add a full-text search to render all the images that contain a text input. For simplicity, use SQLite. 🔍
You can go a step f…
-
As the title says, the KNN function does not return the nearest neighbour for me in many cases.
I noticed this when I created N number of random points and a random searchpoint, all within the boun…
-
Our t-SNE implementation is `O(n²)`. There is Barnes-Hut implementation, which is `O(n)`, but it requires quad-trees which are not trivial to reproduce with Nx. However, there is [a CUDA implementatio…
-
-
I'm trying to use ONNX format as an universal container for models transfer, and I've found that I'm not able to export a simple kNN model with cosine distance, which is very common in NLP:
```pyth…
-
In the Python version of the book we teach how to get the K largest / smallest values by using
- `sort_values` + `head`
- `nlargest`/`nsmallest` (NB: this is slightly more efficient. O(N) instead of…
-
I get this error whenever I run claspy segmentation in Jupyter notebooks after restarting kernel.
If I run it again **without changing anything**, it runs fine.
Do you have any idea what might cau…