Should I use a sequence input layer or an image input layer for a combined CNN/LSTM neural network?

68 次查看（过去 30 天）

Jade 2024-11-6，16:05

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2164400-should-i-use-a-sequence-input-layer-or-an-image-input-layer-for-a-combined-cnn-lstm-neural-network

评论： Jade 2024-11-7，21:43

I am attempting to use a CNN/LSTM to take in a series of frames from a video of two liquids mixing together to predict their viscosities.

My initial layout is shown in the attached image and I planned on seperating a cell array of frames into stacks of sequences to use as inputs.

I was told that this would not work and an alternative approach is to use 2D or 3D (not sure which) image input layers and then use time as a seperate input for the LSTM portion. I'm not sure I understand what this means or why my approach was said to be wrong.

Which, if any, approach is best? Also, if neither of them are, is there a better method?

4 个评论
显示 2更早的评论隐藏 2更早的评论

Matt J 2024-11-7，20:08

OK, well it doesn't look like network analyzer is showing any errors. Is there something that's not working?

Jade 2024-11-7，21:43

Matt,

It seems to run with 1 video so far, and I'm in the process of scaling it up now. Training loss returned NaN at first, but adjusting the learning rate seems to have solved that issue.

Just wanted to make sure this was the correct approach to the problem before going too far in the wrong direction. There's a lot of different network structures and I'm still learning. Really appreciate the help!

请先登录，再进行评论。

请先登录，再回答此问题。