Home | Trees | Indices | Help |
|
---|
|
Node which uses the data history during training to learn cutoff values. As opposed to the simple CutoffNode, a different cutoff value is learned for each data coordinate. For example if an upper cutoff fraction of 0.05 is specified, then the upper cutoff bound is set so that the upper 5% of the training data would have been clipped (in each dimension). The cutoff bounds are then applied during execution. This Node also works as a HistogramNode, so the histogram data is stored. When stop_training is called the cutoff values for each coordinate are calculated based on the collected histogram data.
|
|||
Inherited from Node | |||
---|---|---|---|
__metaclass__ This Metaclass is meant to overwrite doc strings of methods like execute, stop_training, inverse with the ones defined in the corresponding private methods _execute, _stop_training, _inverse, etc... |
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
Inherited from |
|||
Inherited from HistogramNode | |||
---|---|---|---|
|
|||
|
|||
Inherited from Node | |||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|
|||
Inherited from |
|||
Inherited from Node | |||
---|---|---|---|
_train_seq List of tuples: [(training-phase1, stop-training-phase1), (training-phase2, stop_training-phase2), ... |
|||
dtype dtype |
|||
input_dim Input dimensions |
|||
output_dim Output dimensions |
|||
supported_dtypes Supported dtypes |
|
Initialize the node. lower_cutoff_fraction -- Fraction of data that will be cut off after the training phase (assuming the data distribution does not change). If set to None (default value) no cutoff is performed. upper_cutoff_fraction -- Works like lower_cutoff_fraction. hist_fraction -- Defines the fraction of the data that is stored for the histogram. hist_filename -- Filename for the file to which the data history will be pickled after training. The data is pickled when stop_training is called and data_hist is then cleared (to free memory). If filename is None (default value) then data_hist is not cleared and can be directly used after training.
|
Return the clipped data.
|
Calculate the cutoff bounds based on collected histogram data.
|
Return the clipped data.
|
Calculate the cutoff bounds based on collected histogram data.
|
Home | Trees | Indices | Help |
|
---|
Generated by Epydoc 3.0.1 on Fri Oct 9 06:08:51 2009 | http://epydoc.sourceforge.net |