GitLab

Corrected dropout and output layer (include sigmoid). Added learning_rate_decay again since it is indeed supported in Caffe2

Added indented block in all layer templates due to changes made in CNNCreator.ftl in order to avoid a python error

Bugfix: ${input} in convolution template (case: input same as data input) should not be a reference anymore due to the new version of the add_input function.
Test must be made with Blob "data" always due to the new version of the add_input function.

Modified Pooling.ftl: Adapted stride and kernel parameters with same and different height and width.

Corrected Convolution, Pooling and FullyConnected layer templates: Adapted stride with same and different height and width in convolution and pooling layers. Corrected dim_in value in convolution and fullyconnected layers.

Updated pom: cnn-arch version changed to 0.2.3-SNAPSHOT and cnn-train version changed to 0.2.4-SNAPSHOT.
Minor changes in pooling layers.