How to chose convolutional network size to fit in memory?

Question

Denys Li 2017-8-11

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/352475-how-to-chose-convolutional-network-size-to-fit-in-memory

评论： Mity sosi 2019-5-11

Hi,

I am trying to use NN toolbox with convolutional layer for regression problem, specifically depth estimation from image. For this, I want to use 256x256 as input and kind of smaller size for output but still can't fit into RAM. What i need to do to chose best sizes of layers?

Another question, why I cant use datastores(without loading images into RAM) with Regression Layer?

Thanks for attention

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Mity sosi 2019-5-11

Hi

Can you expalin how to define ' your regressors in the other columns ' , I do not know it . because I have the same problem.

Thanks

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Amy 2017-8-14

2
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/352475-how-to-chose-convolutional-network-size-to-fit-in-memory#answer_277979

Hi Denys,

See https://www.mathworks.com/help/nnet/ug/layers-of-a-convolutional-neural-network.html for information on defining layers for your convolutional neural network.

In a CNN, the majority of the weights are held by the fully connected layers. The convolutional layers in the network convert spatial information into more compact semantic information. Pooling layers then downsample redundant information so that when you reach fully connected layers they are receiving fewer activations.

I am not sure what your CNN looks like, but if you have fewer convolutional layers in your network, your last fully connected layer ends up with a greater number of weights. This could be what is causing you to run out of RAM.

As an example, you could refer to the layers in the AlexNet network for ideas for defining your network layers: https://www.mathworks.com/help/nnet/examples/visualize-features-of-a-convolutional-neural-network.html

As for using image datastores, you can use them with a regression layer without loading them into memory. For now, you can get the image file names from the datastore, then create a table with the file names in the first column and your regressors in the other columns, and feed that to trainNetwork.