With the new year, the new version of ANNdotNET has come. This is mayor updates which brings very exciting features.
Here are what has come with the ANNdotNET v1.2:
Image classification module:- this is the main update to this version. Previously you could run image processing only when you manually create mlconfig file, with text based reader. Now you can perform full image preparation prior to create mlconfig file. For example Cat&Dog image processing deep learning example is provided and can be found at ANNdotNET Start page. Notice: prior to run this example you should download image dataset from Kaggle web site and save it on specific location on you disk. More information can be found at ProjectInfo tab (see image below).
ANNdotNET Feed: brings ability to share interesting
annproject‘s to all community. Once the interesting project is added to ANNdotNET Feed it can be viewed by all uses that have installed ANNdotNET v1.2+ version. Currently three examples are provided through ANNdotNET Feed.
Time Series Generator– previously time series could be loaded in
Data Importdialog only with one column data without header. Now, more than one column with header can be imported, and only the last one will be generated as time series, while the rest columns will remain as are.
- Split Raw Data Set to:
testsets. Up to now the user could split raw data set on train and validation sets only.
- Export to Excel with all three data sets. In case test data set is defined, Export to Excel will also export data set for testing.
- Optimization data loading and handling with huge data set.There are some improvements in loading huge data set.
- Visual Network Designer improvements. Visual Network Designer now is provided by more options.
- Added new Layer types: Convolution, Pooling, etc.
- Insert button Insert Layer in the network at specific position.
- Some WinForms Dialogs has been converted into WPF based windows in order to fix WInForm DPI issue on scalled monitors. #42
- Minor code improvements and bug fixes
In case you like this project, go to http://github.com/bhrnjica/anndotnet and download the latest version, and dont forget to give a star.