"Kevin" Seung Whan Chung
"Kevin" Seung Whan Chung
# Neural network module `lasdi.networks` module provides various NN modules that can be combined into encoder/decoder. - `MultiLayerPerceptron` class is moved from previous `lasdi.latent_space` module. - `CNN2D` class is newly...
Per @punkduckable , multihead attention should be implemented as a layer, not an activation function. However, the current implementation simply uses multihead attention as an activation function, which also disrupts...
Currently workflow driver for offline FOM does not need to specify the stage to run. While the intention was to reduce the job-scripting effort, it can make the job script...