Simon Hessner

In experiment.py you define M_N like this ```python train_loss = self.model.loss_function(*results, M_N = self.params['batch_size']/ self.num_train_imgs, optimizer_idx=optimizer_idx, batch_idx = batch_idx) ``` M_N is then used as a weighting factor for the...

When using the current version of the repository with Python 3.9, the fractions.gcd function can't be found. This is because this function was deprecated in Version 3.5 and has been...

Units in the dataset

1

Hi, what is 1 unit in the LAFAN1 dataset in "real world" metrics? Is it 1cm / 1 inch / 1 meter or something completely different? We need to know...

More detailed error messages for KNN model training

3

When training a KNN model using the `/_plugins/_knn/models/{model_name}/_train` POST endpoint, often the error message returned by `GET /_plugins/_knn/models/{model_name}` just says > Failed to execute training. May be caused by an...

[BUG] GET /_plugins/_knn/*/stats returns incomplete / wrong information about graphs

1

### Describe the bug We have a cluster with 10 nodes, running OpenSearch 2.13. Currently there are two indexes that have knn fields. One index uses FAISS HNSW with SQ...