tensorflow_estimator/python/estimator/canned/linear_testing_utils.py [239:329]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - metric_keys.MetricKeys.LOSS_MEAN: 9., metric_keys.MetricKeys.PREDICTION_MEAN: 13., metric_keys.MetricKeys.LABEL_MEAN: 10., tf.compat.v1.GraphKeys.GLOBAL_STEP: 100 }, eval_metrics) def test_evaluation_for_multi_dimensions(self): x_dim = 3 label_dim = 2 with tf.Graph().as_default(): tf.Variable([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]], name=AGE_WEIGHT_NAME) tf.Variable([7.0, 8.0], name=BIAS_NAME) tf.Variable(100, name='global_step', dtype=tf.dtypes.int64) save_variables_to_ckpt(self._model_dir) linear_regressor = self._linear_regressor_fn( feature_columns=(self._fc_lib.numeric_column('age', shape=(x_dim,)),), label_dimension=label_dim, model_dir=self._model_dir) input_fn = numpy_io.numpy_input_fn( x={ 'age': np.array([[2., 4., 5.]]), }, y=np.array([[46., 58.]]), batch_size=1, num_epochs=None, shuffle=False) eval_metrics = linear_regressor.evaluate(input_fn=input_fn, steps=1) self.assertItemsEqual( (metric_keys.MetricKeys.LOSS, metric_keys.MetricKeys.LOSS_MEAN, metric_keys.MetricKeys.PREDICTION_MEAN, metric_keys.MetricKeys.LABEL_MEAN, tf.compat.v1.GraphKeys.GLOBAL_STEP), eval_metrics.keys()) # Logit is # [2., 4., 5.] * [1.0, 2.0] + [7.0, 8.0] = [39, 50] + [7.0, 8.0] # [3.0, 4.0] # [5.0, 6.0] # which is [46, 58] self.assertAlmostEqual(0, eval_metrics[metric_keys.MetricKeys.LOSS]) def test_evaluation_for_multiple_feature_columns(self): with tf.Graph().as_default(): tf.Variable([[10.0]], name=AGE_WEIGHT_NAME) tf.Variable([[2.0]], name=HEIGHT_WEIGHT_NAME) tf.Variable([5.0], name=BIAS_NAME) tf.Variable( 100, name=tf.compat.v1.GraphKeys.GLOBAL_STEP, dtype=tf.dtypes.int64) save_variables_to_ckpt(self._model_dir) batch_size = 2 feature_columns = [ self._fc_lib.numeric_column('age'), self._fc_lib.numeric_column('height') ] input_fn = numpy_io.numpy_input_fn( x={ 'age': np.array([20, 40]), 'height': np.array([4, 8]) }, y=np.array([[213.], [421.]]), batch_size=batch_size, num_epochs=None, shuffle=False) est = self._linear_regressor_fn( feature_columns=feature_columns, model_dir=self._model_dir) eval_metrics = est.evaluate(input_fn=input_fn, steps=1) self.assertItemsEqual( (metric_keys.MetricKeys.LOSS, metric_keys.MetricKeys.LOSS_MEAN, metric_keys.MetricKeys.PREDICTION_MEAN, metric_keys.MetricKeys.LABEL_MEAN, tf.compat.v1.GraphKeys.GLOBAL_STEP), eval_metrics.keys()) # Logit is [(20. * 10.0 + 4 * 2.0 + 5.0), (40. * 10.0 + 8 * 2.0 + 5.0)] = # [213.0, 421.0], while label is [213., 421.]. Loss = 0. self.assertAlmostEqual(0, eval_metrics[metric_keys.MetricKeys.LOSS]) def test_evaluation_for_multiple_feature_columns_mix(self): with tf.Graph().as_default(): tf.Variable([[10.0]], name=AGE_WEIGHT_NAME) tf.Variable([[2.0]], name=HEIGHT_WEIGHT_NAME) tf.Variable([5.0], name=BIAS_NAME) tf.Variable( 100, name=tf.compat.v1.GraphKeys.GLOBAL_STEP, dtype=tf.dtypes.int64) save_variables_to_ckpt(self._model_dir) batch_size = 2 feature_columns = [ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - tensorflow_estimator/python/estimator/canned/v1/linear_testing_utils_v1.py [316:406]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - metric_keys.MetricKeys.LOSS_MEAN: 9., metric_keys.MetricKeys.PREDICTION_MEAN: 13., metric_keys.MetricKeys.LABEL_MEAN: 10., tf.compat.v1.GraphKeys.GLOBAL_STEP: 100 }, eval_metrics) def test_evaluation_for_multi_dimensions(self): x_dim = 3 label_dim = 2 with tf.Graph().as_default(): tf.Variable([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]], name=AGE_WEIGHT_NAME) tf.Variable([7.0, 8.0], name=BIAS_NAME) tf.Variable(100, name='global_step', dtype=tf.dtypes.int64) save_variables_to_ckpt(self._model_dir) linear_regressor = self._linear_regressor_fn( feature_columns=(self._fc_lib.numeric_column('age', shape=(x_dim,)),), label_dimension=label_dim, model_dir=self._model_dir) input_fn = numpy_io.numpy_input_fn( x={ 'age': np.array([[2., 4., 5.]]), }, y=np.array([[46., 58.]]), batch_size=1, num_epochs=None, shuffle=False) eval_metrics = linear_regressor.evaluate(input_fn=input_fn, steps=1) self.assertItemsEqual( (metric_keys.MetricKeys.LOSS, metric_keys.MetricKeys.LOSS_MEAN, metric_keys.MetricKeys.PREDICTION_MEAN, metric_keys.MetricKeys.LABEL_MEAN, tf.compat.v1.GraphKeys.GLOBAL_STEP), eval_metrics.keys()) # Logit is # [2., 4., 5.] * [1.0, 2.0] + [7.0, 8.0] = [39, 50] + [7.0, 8.0] # [3.0, 4.0] # [5.0, 6.0] # which is [46, 58] self.assertAlmostEqual(0, eval_metrics[metric_keys.MetricKeys.LOSS]) def test_evaluation_for_multiple_feature_columns(self): with tf.Graph().as_default(): tf.Variable([[10.0]], name=AGE_WEIGHT_NAME) tf.Variable([[2.0]], name=HEIGHT_WEIGHT_NAME) tf.Variable([5.0], name=BIAS_NAME) tf.Variable( 100, name=tf.compat.v1.GraphKeys.GLOBAL_STEP, dtype=tf.dtypes.int64) save_variables_to_ckpt(self._model_dir) batch_size = 2 feature_columns = [ self._fc_lib.numeric_column('age'), self._fc_lib.numeric_column('height') ] input_fn = numpy_io.numpy_input_fn( x={ 'age': np.array([20, 40]), 'height': np.array([4, 8]) }, y=np.array([[213.], [421.]]), batch_size=batch_size, num_epochs=None, shuffle=False) est = self._linear_regressor_fn( feature_columns=feature_columns, model_dir=self._model_dir) eval_metrics = est.evaluate(input_fn=input_fn, steps=1) self.assertItemsEqual( (metric_keys.MetricKeys.LOSS, metric_keys.MetricKeys.LOSS_MEAN, metric_keys.MetricKeys.PREDICTION_MEAN, metric_keys.MetricKeys.LABEL_MEAN, tf.compat.v1.GraphKeys.GLOBAL_STEP), eval_metrics.keys()) # Logit is [(20. * 10.0 + 4 * 2.0 + 5.0), (40. * 10.0 + 8 * 2.0 + 5.0)] = # [213.0, 421.0], while label is [213., 421.]. Loss = 0. self.assertAlmostEqual(0, eval_metrics[metric_keys.MetricKeys.LOSS]) def test_evaluation_for_multiple_feature_columns_mix(self): with tf.Graph().as_default(): tf.Variable([[10.0]], name=AGE_WEIGHT_NAME) tf.Variable([[2.0]], name=HEIGHT_WEIGHT_NAME) tf.Variable([5.0], name=BIAS_NAME) tf.Variable( 100, name=tf.compat.v1.GraphKeys.GLOBAL_STEP, dtype=tf.dtypes.int64) save_variables_to_ckpt(self._model_dir) batch_size = 2 feature_columns = [ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -