In detail, given the adjacency matrix W and the node degree matrix D, the propagation is iteratively computed using the following formula: Implementation and training The model was implemented using the Python and PyTorch50 (v.2.1.1) deep learning framework. Specifically, the graph convolution ...
Data, weights, and code for running the TAPE benchmark on a trained protein embedding. We provide a pretraining corpus, five supervised downstream tasks, pretrained language model weights, and benchmarking code. This code has been updated to use pytorch - as such previous pretrained model weights...
The model was implemented using the Python and PyTorch50(v.2.1.1) deep learning framework. Specifically, the graph convolution layers were implemented using the torch-geometric package51(v.2.1.1). To optimize the model during the training process, the Adam optimizer with a learning rate of 0.00...
You will also need to install PyTorch (we tested our models onv2.0.1), PyTorch Geometric, and PyTorch Scatter. We provide a notebook with installation guidance that can be found inexamples/evodiff.ipynb. It also includes examples on how to generate a smaller number of sequences and MSAs ...
.github/workflows add workflow to upload to pypi Sep 7, 2021 config fix merge conflict Oct 16, 2019 examples rename tape_pytorch -> tape Dec 8, 2019 scripts remove unused files Dec 9, 2019 tape much stable Nov 4, 2023 tests changed tests Jun 26, 2020 .gitignore add more datafile types...