-
Will need to use the section "extend to other distance measures" from the sDBSCAN paper
-
I think the L2_distances in the function _nearest_neighbour_correct_ should be computed as follows:
`dis = pairs[0][i] - pairs[1][i]`
`dis = dis.reshape(dis.size)`
`L2_distances[i] = np.sqrt(dis.do…
-
This is a follow up to this [thread](https://github.com/davidsandberg/facenet/issues/591)
I'm not talking about custom classifier from @davidsandberg (i.e. training classifier on known classes).. …
-
Hi,
I'm trying to implement an L2-distances module. The code below prints:
```
function: 0x41cd5570
3.999683343136
```
which means the gradient check doesn't pass. What am I missing?
``` lua
autog…
-
# Summary
Running searches against a GPU index using `normalize_L2` is heavily CPU intensive.
Please refer to the following psuedo code:
```
def setup_index(numpy_array):
res = faiss.St…
-
### Problem Description
Some applications call for a *partially* fuzzy join, meaning fuzzy joining within groups of exactly matched entities.
For instance, matching loans from two tables of user…
-
Hi, thank you for this excellent work, I am already using it in my project which shows impressive results.
I just want to ask about the training objective:
https://github.com/facebookresearch/Q…
-
dists = l2_dist.forward(embed_anchor, embed_pos)
distances.append(dists.data.cpu().numpy())
labels.append(np.ones(dists.size(0)))
dists = l2_dist.forward(e…
-
The functions
`compute_distances_two_loops`
`compute_distances_one_loops`
`compute_distances_no_loops`
all are required to compute the L2 distance so the dists matrix should be prepended…
-
Right now only cosine is supported, but it would be great to have support for L2 as well.