Grouped Pointwise Convolutions Reduce Parameters in Convolutional Neural Networks
In DCNNs, the number of parameters in pointwise convolutions rapidly grows due to the multiplication of the number of filters by the number of input channels that come from the previous layer. Our proposal makes pointwise convolutions parameter efficient via grouping filters into parallel branches...
Na minha lista:
| Principais autores: | , , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado em: |
Brno University of Technology
2022-06-01
|
| coleção: | Mendel |
| Assuntos: | |
| Acesso em linha: | https://mendel-journal.org/index.php/mendel/article/view/169 |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|