pinot
pinot copied to clipboard
choderalab
Probabilistic Inference for NOvel Therapeutics
Example usage can be found in `scripts/gp/gp_playground_gpytorch.ipynb` ``` net_variational_gp = pinot.Net( pinot.representation.Sequential( pinot.representation.dgl_legacy.gn(kwargs={"allow_zero_in_degree":True}), [64, 'relu', 64, 'relu', 64, 'relu']), output_regressor_class=pinot.regressors.VariationalGP, num_inducing_points=150, num_data=902, beta = beta, ) lr = 1e-4 optimizer...
Hi, Looks like if I specify any `embedding_dim` other than `64` would result in an error? For example, ``` import torch import pinot import numpy as np ds = pinot.data.moonshot()...
Let's think about how can we get the statistics across multiple test set data points without using this `_independent` helper function.
what features do we want for `Dataset` object? now we have the following functionalities - [ ] csv import - [ ] batch - [ ] split - [ ]...
the TODO list to make our repo prettier, cleaner, and more user-friendly before moving forward - [ ] a short manifest @yuanqing-wang @jchodera - [ ] examples (scripts and/or notebooks?)...
# Generative model Generative model implementation: https://github.com/choderalab/pinot/blob/master/pinot/generative/torch_gvae/model.py Encoder: One input graph g with node features. For each node feature: 1. A linear layer maps the node feature from 117 dimensions...
we decided that for now we are going to pass only features in our message passing framework. this is safer but might add complexity in the future when we also...
Let's discuss what kind of features should we input. Now it's a one-hot encoding of the element identity plus some atom property flags. https://github.com/choderalab/pinot/blob/master/pinot/graph.py