grace
grace copied to clipboard
alan-turing-institute
Graph Representation Analysis for Connected Embeddings
We should consider using a KNN to construct the intial graph, and compare this with the current triangulation method. https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.pool.knn_graph.html#torch_geometric.nn.pool.knn_graph This would have the additional benefit of allowing alternative hypotheses...
To be easily citable, GitHub has this option (as explained here: https://academia.stackexchange.com/questions/14010/how-do-you-cite-a-github-repository)
**Describe the issue here**
* Read IoU scores list from `metrics.json` * Violin plot with mean & median values per each time-stamped run * Compare the runs in batches
To be placed in `grace/utils/` subfolder. Descriptive doc to introduce what the image / graph augmentations do, how they can be applied, a reasonable range of their respective parameters, etc....
**Describe the issue here**
Nice for people to follow certain community standards & include templates for collaborative work, such as PR reviews. Adding @aldenc as an assignee to discuss TheTuringWay templates & what to...
Required check for `__post_init__`
Probably insert into `grace.io.core`
Metadata
Owner
Metadata
Graph Representation Analysis for Connected Embeddings