How to build a single-object localization CNN based-on an object classification network?
2 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Hi all,
I'm new to convolutional neural network. I'm trying to use Alexnet to build a single object localization network, which I think is a simple problem in this area. What I did is to replace the last three layers of Alexnet, which are fullyConnnectedLayer(1000), softmaxLayer, and classificationLayer, with two layers, which are fullyConnectedLayer(4) and regressionLayer. Did I do it right? When I tried to train this network, the result seems wrong. Specifically, the Mini-batch Loss and the Mini-batch RMSE were NaN all the time. What would be the reason for this?
Thank you in advance!
Shuwei.
0 comentarios
Respuestas (1)
Ankitha Kollegal Arjun
el 28 de Jul. de 2017
If the regression response values are very big and/or you have many regressors, your loss will become large, and it eventually leads to NaNs. This is the reason your Mini-batch Loss and the Mini-batch RMSE are NaN.
There are two workarounds which might fix the issue. Try one of the following:
1. Lower the initial learning rate. See more details on the initial learning rate here:
2. Normalize the responses so that the maximum value is 1. You can use the function "normc" for this:
Hope this helps!
Ver también
Categorías
Más información sobre Image Data Workflows en Help Center y File Exchange.
Productos
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!