Stefan Maetschke

Entering text into a text box of a dialog (e.g. add layer) triggers hot keys. Hot keys should only work when focus is on oct panel

Add other/improved method to balance class distributions

2

https://www.analyticsvidhya.com/blog/2017/03/imbalanced-classification-problem/?utm_source=feedburner&utm_medium=email&utm_campaign=Feed%3A+AnalyticsVidhya+%28Analytics+Vidhya%29

Implement NetworkPytorch wrapper

for instance, this does not work (but should) load_images >> ViewImage() >> Prefetch() >> Consume() The following works: load_images >> Prefetch() >> ViewImage() >> Consume Similarly the moment a BuildBatch()...

Due to the chained, wrapped iterators wrongly composed pipelines often produce cryptic error messages. Adding assertions on input data and catching common errors should lead to more informative messages.

BuildBatch.by() has been replaced by BuildBatch.input() and BuildBatch.output()

Test for PlotLines in tests/nutsml/plotter.py is currently disabled because the test runs fine individually but fails when running as part of the test suite. Unclear if that is a matplotlib...

Get output/activation of a network layer

1

Example code for Keras: @nut_function def GetActivations(batch, model, layer, istrain=1): from keras import backend as K f = K.function([model.input, K.learning_phase()], [model.get_layer(layer).output]) return f([batch[0], istrain]) build_batch >> GetActivations(network.model) >> FlattenCol(0) >>...

Add TFLearnNetwork(model) to wrap tensorflow models created with TFLearn: http://tflearn.org/