Query about weight filter size in AlexNet
2 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
deepika s
el 14 de Ag. de 2021
Comentada: deepika s
el 18 de Ag. de 2021
I have analysed the pretrained alexnet model. I have attached the screen shot. In that conv2 row, weights are given as 5*5*48*256. what is 48 here?. As per my knowledge, 48 represents the previous layer (number of channels in previous layer). but number of previous layer is 96 after pool1. likewise, same doubt in conv4 and conv5.
Can anyone explain this question?
0 comentarios
Respuesta aceptada
Harikrishnan Balachandran Nair
el 17 de Ag. de 2021
The reason that the third dimension of weights in the mentioned layer is not the same as the number of channels in input is that the corresponding layer in AlexNet perform grouped Convolution. You can refer to the following Documentation to learn more about AlexNet : https://www.mathworks.com/help/deeplearning/ref/alexnet.html.
Más respuestas (0)
Ver también
Categorías
Más información sobre Image Data Workflows en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!