Add new metrics and metrics tests

keras/metrics.py

@@ -1,3 +1,4 @@
+import numpy as np
 from . import backend as K
 
 
@@ -12,7 +13,70 @@ def categorical_accuracy(y_true, y_pred):
 
 def sparse_categorical_accuracy(y_true, y_pred):
     return K.mean(K.equal(K.max(y_true, axis=-1),
-                          K.argmax(y_pred, axis=-1)))
+                          K.cast(K.argmax(y_pred, axis=-1), K.floatx())))
+
+
+def mean_squared_error(y_true, y_pred):
+    return K.mean(K.square(y_pred - y_true))
+
+
+def mean_absolute_error(y_true, y_pred):
+    return K.mean(K.abs(y_pred - y_true))
+
+
+def mean_absolute_percentage_error(y_true, y_pred):
+    diff = K.abs((y_true - y_pred) / K.clip(K.abs(y_true), K.epsilon(), np.inf))
+    return 100. * K.mean(diff)
+
+
+def mean_squared_logarithmic_error(y_true, y_pred):
+    first_log = K.log(K.clip(y_pred, K.epsilon(), np.inf) + 1.)
+    second_log = K.log(K.clip(y_true, K.epsilon(), np.inf) + 1.)
+    return K.mean(K.square(first_log - second_log))
+
+
+def squared_hinge(y_true, y_pred):
+    return K.mean(K.square(K.maximum(1. - y_true * y_pred, 0.)))
+
+
+def hinge(y_true, y_pred):
+    return K.mean(K.maximum(1. - y_true * y_pred, 0.))
+
+
+def categorical_crossentropy(y_true, y_pred):
+    '''Expects a binary class matrix instead of a vector of scalar classes.
+    '''
+    return K.mean(K.categorical_crossentropy(y_pred, y_true))
+
+
+def sparse_categorical_crossentropy(y_true, y_pred):
+    '''expects an array of integer classes.
+    Note: labels shape must have the same number of dimensions as output shape.
+    If you get a shape error, add a length-1 dimension to labels.
+    '''
+    return K.mean(K.sparse_categorical_crossentropy(y_pred, y_true))
+
+
+def binary_crossentropy(y_true, y_pred):
+    return K.mean(K.binary_crossentropy(y_pred, y_true))
+
+
+def poisson(y_true, y_pred):
+    return K.mean(y_pred - y_true * K.log(y_pred + K.epsilon()))
+
+
+def cosine_proximity(y_true, y_pred):
+    y_true = K.l2_normalize(y_true, axis=-1)
+    y_pred = K.l2_normalize(y_pred, axis=-1)
+    return -K.mean(y_true * y_pred)
+
+
+# aliases
+mse = MSE = mean_squared_error
+mae = MAE = mean_absolute_error
+mape = MAPE = mean_absolute_percentage_error
+msle = MSLE = mean_squared_logarithmic_error
+cosine = cosine_proximity
 
 
 from .utils.generic_utils import get_from_module

tests/keras/test_metrics.py

@@ -0,0 +1,44 @@
+import pytest
+import numpy as np
+
+from keras import metrics
+from keras import backend as K
+
+all_metrics = [
+    metrics.binary_accuracy,
+    metrics.categorical_accuracy,
+    metrics.mean_squared_error,
+    metrics.mean_absolute_error,
+    metrics.mean_absolute_percentage_error,
+    metrics.mean_squared_logarithmic_error,
+    metrics.squared_hinge,
+    metrics.hinge,
+    metrics.categorical_crossentropy,
+    metrics.binary_crossentropy,
+    metrics.poisson,
+    metrics.cosine_proximity,
+]
+
+all_sparse_metrics = [
+    metrics.sparse_categorical_accuracy,
+    metrics.sparse_categorical_crossentropy,
+]
+
+
+def test_metrics():
+    y_a = K.variable(np.random.random((6, 7)))
+    y_b = K.variable(np.random.random((6, 7)))
+    for metric in all_metrics:
+        output = metric(y_a, y_b)
+        assert K.eval(output).shape == ()
+
+
+def test_sparse_metrics():
+    for metric in all_sparse_metrics:
+        y_a = K.variable(np.random.randint(0, 7, (6,)), dtype=K.floatx())
+        y_b = K.variable(np.random.random((6, 7)), dtype=K.floatx())
+        assert K.eval(metric(y_a, y_b)).shape == ()
+
+
+if __name__ == "__main__":
+    pytest.main([__file__])