def _get_compiled_multi_io_model(self):
model = get_multi_io_model()
model.compile(
optimizer='rmsprop',
loss='mse',
metrics=[metrics.MeanSquaredError(name='mean_squared_error')],
weighted_metrics=[
metrics.MeanSquaredError(name='mean_squared_error_2')
],
run_eagerly=testing_utils.should_run_eagerly())
return model
def _get_model(self):
x = layers.Dense(3, kernel_initializer='ones', trainable=False)
out = layers.Dense(
1, kernel_initializer='ones', name='output', trainable=False)
model = testing_utils.get_model_from_layers([x, out], input_shape=(1,))
model.compile(
optimizer='rmsprop',
loss='mse',
metrics=[metrics.MeanSquaredError()],
weighted_metrics=[metrics.MeanSquaredError()],
run_eagerly=testing_utils.should_run_eagerly())
return model
def test_config(self):
mse_obj = metrics.MeanSquaredError(name='my_mse', dtype=dtypes.int32)
self.assertEqual(mse_obj.name, 'my_mse')
self.assertEqual(mse_obj._dtype, dtypes.int32)
# Check save and restore config
mse_obj2 = metrics.MeanSquaredError.from_config(mse_obj.get_config())
self.assertEqual(mse_obj2.name, 'my_mse')
self.assertEqual(mse_obj2._dtype, dtypes.int32)
def test_weighted(self):
mse_obj = metrics.MeanSquaredError()
self.evaluate(variables.variables_initializer(mse_obj.variables))
y_true = constant_op.constant(((0, 1, 0, 1, 0), (0, 0, 1, 1, 1),
(1, 1, 1, 1, 0), (0, 0, 0, 0, 1)))
y_pred = constant_op.constant(((0, 0, 1, 1, 0), (1, 1, 1, 1, 1),
(0, 1, 0, 1, 0), (1, 1, 1, 1, 1)))
sample_weight = constant_op.constant((1., 1.5, 2., 2.5))
result = mse_obj(y_true, y_pred, sample_weight=sample_weight)
self.assertAllClose(0.54285, self.evaluate(result), atol=1e-5)
def _get_multi_io_model(self):
inp_1 = layers.Input(shape=(1,), name='input_1')
inp_2 = layers.Input(shape=(1,), name='input_2')
x = layers.Dense(3, kernel_initializer='ones', trainable=False)
out_1 = layers.Dense(
1, kernel_initializer='ones', name='output_1', trainable=False)
out_2 = layers.Dense(
1, kernel_initializer='ones', name='output_2', trainable=False)
branch_a = [inp_1, x, out_1]
branch_b = [inp_2, x, out_2]
model = testing_utils.get_multi_io_model(branch_a, branch_b)
model.compile(
optimizer='rmsprop',
loss='mse',
metrics=[metrics.MeanSquaredError()],
weighted_metrics=[metrics.MeanSquaredError()],
run_eagerly=testing_utils.should_run_eagerly())
return model
def test_unweighted(self):
mse_obj = metrics.MeanSquaredError()
self.evaluate(variables.variables_initializer(mse_obj.variables))
y_true = constant_op.constant(((0, 1, 0, 1, 0), (0, 0, 1, 1, 1),
(1, 1, 1, 1, 0), (0, 0, 0, 0, 1)))
y_pred = constant_op.constant(((0, 0, 1, 1, 0), (1, 1, 1, 1, 1),
(0, 1, 0, 1, 0), (1, 1, 1, 1, 1)))
update_op = mse_obj.update_state(y_true, y_pred)
self.evaluate(update_op)
result = mse_obj.result()
self.assertAllClose(0.5, result, atol=1e-5)
