How to use Deep Network Designer for training testing network?

5 次查看（过去 30 天）
Joyjit Chatterjee
Joyjit Chatterjee 2019-1-19
I am trying to model a LSTM based network using the Deep Network Designer Toolbox in MATLAB. I have designed the network LSTM Network Architecture for Classification as given in https://uk.mathworks.com/help/deeplearning/ug/long-short-term-memory-networks.html . The network starts with a sequence input layer followed by an LSTM layer. To predict class labels, the network ends with a fully connected layer, a softmax layer, and a classification output layer. I have divided my data into predictors of dimensions 100x21392 double and Tvec (response of dimensions 14x21392 sparse for 14 classes of output labels). I would like to train and test the network but am completely clueless. I have referred to other documentation on https://uk.mathworks.com/help/deeplearning/ug/long-short-term-memory-networks.html but am confused as to how I can shape my data to be able to be used for this purpose. I exported the 5x1 Layer from Deep Network Designer toolbox into the workspace, but after that I am not able to understand as to how I can train/test the network. Any help in this regard would be most appreciated. Cheers!

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Pattern Recognition 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