dagli
dagli copied to clipboard
linkedin
Framework for defining machine learning models, including feature generation and transformations, as directed acyclic graphs (DAGs).
Reading about multilabel problems because of inbalanced label-distribution in training data: https://arxiv.org/abs/2109.04712 A label-based loss-function re-weighting is proposed. It seems that at least applying a weights-array is possible with dl4j?...
I had some problems to output the dl4j computationGraph.summary(). After configuring the logging right, I succeeded to output it for training. But still, after deserializing the prepared dag, something like...
I try to do feature matching on html-document-nodes, and use features of these document nodes (tagname, text, class, length,..) as placeholder (struct). Currently, the network consists of some fasttext and...
I then printed out all F1-Scores of the ConfusionMatrices-List, which looks as expected, but has some NaN at the end. Something like Threshold: F1-Score 0.1: 0.1 0.2: 0.2 0.4: 0.3...
No matter what I set as logging frequence in "NeuralNetwork" (for example TrainingAmount.minibatches(1) or TrainingAmount.minibatches(300)), every iteration is logged. I have to admit, that I got new hardware, and compiled...
I see this line in AbstractNeuralNetwork.uniqueLayerNames (line 534) ``` String baseName = layer.internalAPI().hasName() ? layer.getClass().getSimpleName() : layer.getName(); ``` This make no sense to me. Should it be the other way...