search

modern-fortran / neural-fortran

A parallel framework for deep learning
MIT License
395 stars 82 forks source link

Implement locally connected layer (1-d) #171

Open milancurcic opened 6 months ago

milancurcic commented 6 months ago

Like convolutional, except that each window has its own set of filters (rather than being convolved into one set of filters).

Keras reference: https://www.tensorflow.org/api_docs/python/tf/keras/layers/LocallyConnected1D