Tomasz Bartczak
Tomasz Bartczak
After doing a rename refactoring - the name of this parameter in the docstrings should change as well, currently it stays intact, and one need to change it manually
When using branching model it may happen that release is created, some commits are applied to it, but then it is abandoned - i.e. not deployed to production, but all...
additionally allows to reduce with `sum` to account for the metrics/losses divided by global batch size - when training using custom training step and MirroredStrategy. This addresses https://github.com/keras-team/keras/issues/15509
running quiver by default I get exception when waiting for layer visualization: ``` No such file or directory: u'./tmp/convolution2d_2_0_20161112121943_52.16916_21.06839_1000006.jpg.png' ``` seeing that I created ./tmp and after that it works...
Global Average and Max Pooling are used as an alternative to FC layers. they are very handy for vizualization. what quiver can do is show the convolution layers output that...
currently `iterative_train_test_split` just accepts numpy arrays, both as X and y. It is sometimes useful do the split when X is a pd.Dataframe. It would be good to have this...
Hello there! thanks for the tool, looks promising. nice thing that it works on historical events data! I tried that and got a 'Max memory which an executor could have...
Fills in the docs related to newly introduced `distribute_reduction_method` in the model for distributed training with custom train_step. Valid together with https://github.com/keras-team/keras/pull/16664
having a build file: ``` lazy val root = (project in file(".")). settings( name := "hello", version := "1.0", scalaVersion := "2.11.4", libraryDependencies += "com.github.tomakehurst" % "wiremock" % "1.56" %...
we would benefit from more git commands in Git DSL: 1. create branch from revision/tag 2. push specific branch we currently have some rough implementation of them in class extending...