-
@chthub Thanks for fixing it so quickly. However, other errors come out.
```
python scGNN_v2.py --load_from_10X ~/Documents/filtered_mtx/sham --output_dir ./outputs --total_epoch 31 --featur…
-
Hey Matteo,
thanks for the paper and implementation of the FISHDBC. Great work!
I’ve tried to use it in production but I had problems to pickle the fitted model. Have you tried exporting the fitt…
-
There is an inconsistency with how distance functions for different feature dimensions are handled. When an `egg` is created, the user can optionally pass a `dist_funcs` dictionary containing distanc…
-
Hello, Mr Ren, after reading your paper, as you described in the paper, the gcn`s performance is better than the gat, while in the code, i only discover the cluster code about the gat, in the DGI-HGCN…
YcZ76 updated
3 years ago
-
### Describe the workflow you want to enable
Scikit-learn defines three popular metrics for evaluating clustering performance when there are no ground-truth cluster labels: [sklearn.metrics.silhouett…
-
This is more of a feature request. I see that the [xapi-service](https://github.com/LearningLocker/xapi-service) is containerized which will allow API calls to take place without the need for UI, work…
-
We could add the gmx gromos clustering to MDAnalysis.
The Gromacs doc at [http://manual.gromacs.org/documentation/2020/onlinehelp/gmx-cluster.html](url)
The clustering uses the method as describ…
-
Just a quick FYI.
As installing SAFEclustering into a fresh directory (pointing R_LIBS_USER to a clean directory, to make sure I don't overwrite other stuff), I am unable to run
devtools::inst…
-
- specialize the cache for the cases where we have no clustering key and/or no static row
- use btree instead of rbtree (reduces pointer overhead from 3/node to 1.125/node)
- only store tokens in…
-
Issue tracking the implementation progress of Nearest Neighbors for linfa.
**TODO:**
- [x] Make `kneighbor` implementation more flexible to the specific algorithm chosen (brute force, ball tree, k…