Psion-fanatic/platypush
1
0
Fork 0
forked from platypush/platypush
Code Pull requests Activity

Set default values for metrics for regression and networks

Browse source
This commit is contained in:
Fabio Manganiello 2020-03-23 01:10:59 +01:00
parent 50e372be36
commit f4dcf688f0
1 changed files with 8 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
platypush/plugins/tensorflow/__init__.py
View file

@ -238,7 +238,7 @@ class TensorflowPlugin(Plugin):
you could also pass a dictionary, such as
``metrics={'output_a': 'accuracy', 'output_b': ['accuracy', 'mse']}``. You can also pass a list
``(len = len(outputs))`` of lists of metrics such as ``metrics=[['accuracy'], ['accuracy', 'mse']]`` or
``metrics=['accuracy', ['accuracy', 'mse']]``.
``metrics=['accuracy', ['accuracy', 'mse']]``. Default: ``['accuracy']``.
:param loss_weights: Optional list or dictionary specifying scalar coefficients (Python floats) to weight the
loss contributions of different model outputs. The loss value that will be minimized by the model
@ -370,6 +370,9 @@ class TensorflowPlugin(Plugin):
layer = self._layer_from_dict(layer.pop('type'), **layer)
model.add(layer)
if not metrics:
metrics = ['accuracy']
model.compile(
optimizer=optimizer,
loss=loss,
@ -433,7 +436,7 @@ class TensorflowPlugin(Plugin):
you could also pass a dictionary, such as
``metrics={'output_a': 'accuracy', 'output_b': ['accuracy', 'mse']}``. You can also pass a list
``(len = len(outputs))`` of lists of metrics such as ``metrics=[['accuracy'], ['accuracy', 'mse']]`` or
``metrics=['accuracy', ['accuracy', 'mse']]``.
``metrics=['accuracy', ['accuracy', 'mse']]``. Default: ``['mae', 'mse']``.
:param loss_weights: Optional list or dictionary specifying scalar coefficients (Python floats) to weight the
loss contributions of different model outputs. The loss value that will be minimized by the model
@ -501,6 +504,9 @@ class TensorflowPlugin(Plugin):
else:
model.output_labels = []
if not metrics:
metrics = ['mae', 'mse']
model.compile(
optimizer=optimizer,
loss=loss,