Articles by Yoshiyuki Kobayashi

Project window. Using the EDIT tab

Friday, November 03, 2017

App

Posted by Yoshiyuki Kobayashi

The edit tab is used to edit the network structure of a neural network used for training. Neural Network Console expresses neural network structures using a combination of predefined components (functions) called layers.   1 Adding a new layer to the network graph Drag the layer you want to add to the network graph from the component list on the left side of the edit tab. Or, double-click the layer on the component list. Or, click the layer on the…

Read More

Project window

Friday, November 03, 2017

App

Posted by Yoshiyuki Kobayashi

The project window is used to perform a sequence of Deep Learning development tasks, from project editing and training to evaluation.   Using the project window   1 Returning to the project selection window Click the Home button. Or, press Ctrl+W on the keyboard.   Notes When the project has been edited, a message box appears asking whether you want to save the project.   Notes When training is in progress, a message box appears asking whether you want to…

Read More

Tutorial. Training using a sample project

Friday, November 03, 2017

App

Posted by Yoshiyuki Kobayashi

1 Starting Neural Network Console Double-click on the file neural_network_console.exe in order to execute it.   Reference The first time you run the application, a setup window will open.   2 Opening the sample project From the list of projects that appear when you start the application, select 01_logistic_regression.sdcproj and open it.   Reference The MNIST dataset used in this sample project is downloaded from the following site, and the dataset file is prepared when the sample project is opened…

Read More

Dataset preparation

Friday, November 03, 2017

App

Posted by Yoshiyuki Kobayashi

A dataset is a collection of data used for neural network training and performance evaluation.   Reference Using the sample project included in the Neural Network Console enables you to try a training example without having to create a dataset from scratch. For instructions on how to train using this sample dataset, see “Tutorial.” This section explains how to create a dataset on your own.   Reference The Neural Network Console contains the functionality to create a dataset for image…

Read More

Setup

Friday, November 03, 2017

App

Posted by Yoshiyuki Kobayashi

Unzip sdeep_console_xxx.zip (xxx is the version name) in an appropriate folder of your choice.   Folder and file structure     Notes The Neural Network Console must be placed in a folder that does not include 2-byte (UTF16) characters in its path. The application must be able to write into this folder. The Neural Network Console will not work properly in a folder if it contains 2-byte (UTF16) characters in its path or that is not writable by the application…

Read More