-
## Description
We must implement a robust evaluation suite for the text-based retrieval systems on the `anatomy` split from the [MMLU benchmark](https://huggingface.co/datasets/cais/mmlu).
## Pr…
-
hi, luckycallor, thanks for your code! sorry, i dont read the paper.
evaluate() in evaluate.py
thresholds = np.arange(0, 4, 0.01)
if distance_metric == 1:
thresholdes = np.arang…
-
Progress tends to be tracked by the higher the better especially in scatter…
-
Dear Waymo team,
I notice that when you calculate the distance between agent and road edges, this function ( https://github.com/waymo-research/waymo-open-dataset/blob/5f8a1cd42491210e7de629b6f8fc09…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Environment
```markdown
- Milvus version: master-20240425-f06509bf-amd64
- Deployment mode(standalone or clus…
-
Some metric/feature combinations are inappropriate and will calls AD index calculations to fail. For example, Jaccard distance with RDKit features results in a pairwise distance matrix that is all zer…
-
we implement sd/ssd in both here: https://github.com/neurodata/brainlit/blob/develop/brainlit/algorithms/connect_fragments/trace_evaluation.py
and here: https://github.com/neurodata/brainlit/blob/d…
-
I am trying to fine-tune a SentenceTransformer model on a retrieval dataset using a custom distance metric as the similarity function. My goal is to generate a token_embedding for the query and a sent…
-
Hi,
I am using examples provided in tests/cpp/.
I am trying to add new examples for based on given examples and modify with using cosine metrics for other dataset.
When I try to replace the l2…
-
Currently the (square of the) Euclidean distance is the only metric allowed, with the simplest (i.e., non-wrapping) topology. I'd be interested in getting this to work on e.g. a sphere with the Haver…