Convolutional LSTM (C-LSTM) in MATLAB

67 次查看（过去 30 天）
Jake
Jake 2018-10-9
编辑： Dieter Mayer 2022-8-29
I'd like to train a convolutional neural network with an LSTM layer on the end of it. Similar to what was done in:
  1. https://arxiv.org/pdf/1710.03804.pdf
  2. https://arxiv.org/pdf/1612.01079.pdf
Is this possible?

请先登录，再回答此问题。

回答（5 个）

Shounak Mitra
Shounak Mitra 2018-10-9
Hi Jake,
Unfortunately, we do not directly support C-LSTM. We are working on it and it should be available soon.
-- Shounak
  7 个评论
显示 5更早的评论
David Willingham
David Willingham 2022-8-26
Hi Dieter,
Apologies for not updating this answers post sooner. This workflow is now supported. the following code will illustrated this:
% Load data
[XTrain,YTrain] = japaneseVowelsTrainData;
% Define layers
layers = [ sequenceInputLayer(12,'Normalization','none', 'MinLength', 9);
convolution1dLayer(3, 16)
batchNormalizationLayer()
reluLayer()
maxPooling1dLayer(2)
convolution1dLayer(5, 32)
batchNormalizationLayer()
reluLayer()
averagePooling1dLayer(2)
lstmLayer(100, 'OutputMode', 'last')
fullyConnectedLayer(9)
softmaxLayer()
classificationLayer()];
options = trainingOptions('adam', ...
'MaxEpochs',10, ...
'MiniBatchSize',27, ...
'SequenceLength','longest');
% Train network
net = trainNetwork(XTrain,YTrain,layers,options);
Dieter Mayer
Dieter Mayer 2022-8-29
编辑：Dieter Mayer 2022-8-29
Hi David,
Thanks for your reply! Is this workflow shows a real convolution LSTM (LSTM carries out convolutional operations instead of matrix multiplication) and is not only implied to a input matrix, which is a result of a convolution net work applied before?
Sorry for asking that, I have to learn the syntax of using the deep learning toolbox, I am a beginner. The background is, that I will use such a Conv-LSTM to make precipitation forecasts for grids bases on precipitation radar inputs from several timesteps of the last minutes / hours as discussed in this paper publication

请先登录，再进行评论。

Yi Wei
Yi Wei 2019-12-17
Hi, can matlab support C-LSTM now?
  5 个评论
显示 3更早的评论
ytzhak goussha
ytzhak goussha 2021-2-23
Hey,
Sorry I didn't follow this thread and didn't see the questions.
Here is a simplified C-LSTM network.
The input it a 4D image (height x width x channgle x time)
The input type is sqeuntial.
When you need to put CNN segments, you simply unfold->CNN->Fold->flatten and feed to LSTM layer.
Ioana Cretu
Ioana Cretu 2021-5-18
Hi! When I try to train the model I have this error:
Error using trainNetwork (line 170)
Invalid network.
Caused by:
Layer 'fold': Unconnected output. Each layer output must be connected to the input of another layer.
Detected unconnected outputs:
output 'miniBatchSize'
Layer 'unfold': Unconnected input. Each layer input must be connected to the output of another layer.
I connected the layers using this:
lgraph = layerGraph(Layers);
lgraph = connectLayers(lgraph,'fold/miniBatchSize','unfold/miniBatchSize');
What do you think the cause is?

请先登录，再进行评论。

Chen
Chen 2021-8-25
Please refer to this excellent example in:
Time Series Forecasting Using Hybrid CNN - RNN - File Exchange - MATLAB Central (mathworks.com)
It is possible to train the hybrid together.
Jonathan
Jonathan 2022-8-4
inputSize = [28 28 1];
filterSize = 5;
numFilters = 20;
numHiddenUnits = 200;
numClasses = 10;
layers = [ ...
sequenceInputLayer(inputSize,'Name','input')
sequenceFoldingLayer('Name','fold')
convolution2dLayer(filterSize,numFilters,'Name','conv')
batchNormalizationLayer('Name','bn')
reluLayer('Name','relu')
sequenceUnfoldingLayer('Name','unfold')
flattenLayer('Name','flatten')
lstmLayer(numHiddenUnits,'OutputMode','last','Name','lstm')
fullyConnectedLayer(numClasses, 'Name','fc')
softmaxLayer('Name','softmax')
classificationLayer('Name','classification')];
lgraph = layerGraph(layers);
lgraph = connectLayers(lgraph,'fold/miniBatchSize','unfold/miniBatchSize');
https://www.mathworks.com/help/deeplearning/ug/long-short-term-memory-networks.html
David Willingham
David Willingham 2022-8-26
Updating this answer. This workflow has been supported since R2021. The following example illustrates how to combin CNN's with LSTM layers:
% Load data
[XTrain,YTrain] = japaneseVowelsTrainData;
% Define layers
layers = [ sequenceInputLayer(12,'Normalization','none', 'MinLength', 9);
convolution1dLayer(3, 16)
batchNormalizationLayer()
reluLayer()
maxPooling1dLayer(2)
convolution1dLayer(5, 32)
batchNormalizationLayer()
reluLayer()
averagePooling1dLayer(2)
lstmLayer(100, 'OutputMode', 'last')
fullyConnectedLayer(9)
softmaxLayer()
classificationLayer()];
options = trainingOptions('adam', ...
'MaxEpochs',10, ...
'MiniBatchSize',27, ...
'SequenceLength','longest');
% Train network
net = trainNetwork(XTrain,YTrain,layers,options);

类别

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息

标签

产品


版本

R2018a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by