def test_fit_normalized(self, input_shape, output_dim):
bmr = BernoulliMLPRegressor(input_shape=input_shape,
output_dim=output_dim)
observations, returns = get_train_data(input_shape, output_dim)
for _ in range(150):
bmr.fit(observations, returns)
paths, expected = get_test_data(input_shape, output_dim)
prediction = np.cast['int'](bmr.predict(paths['observations']))
assert np.allclose(prediction, expected, rtol=0, atol=0.1)
x_mean = self.sess.run(bmr.model._networks['default'].x_mean)
x_mean_expected = np.mean(observations, axis=0, keepdims=True)
x_std = self.sess.run(bmr.model._networks['default'].x_std)
x_std_expected = np.std(observations, axis=0, keepdims=True)
assert np.allclose(x_mean, x_mean_expected)
assert np.allclose(x_std, x_std_expected)
def test_is_pickleable(self):
bmr = BernoulliMLPRegressor(input_shape=(1, ), output_dim=2)
with tf.compat.v1.variable_scope(
'BernoulliMLPRegressor/NormalizedInputMLPModel', reuse=True):
bias = tf.compat.v1.get_variable('mlp/hidden_0/bias')
bias.load(tf.ones_like(bias).eval())
bias1 = bias.eval()
result1 = np.cast['int'](bmr.predict(np.ones((1, 1))))
h = pickle.dumps(bmr)
with tf.compat.v1.Session(graph=tf.Graph()):
bmr_pickled = pickle.loads(h)
result2 = np.cast['int'](bmr_pickled.predict(np.ones((1, 1))))
assert np.array_equal(result1, result2)
with tf.compat.v1.variable_scope(
'BernoulliMLPRegressor/NormalizedInputMLPModel',
reuse=True):
bias2 = tf.compat.v1.get_variable('mlp/hidden_0/bias').eval()
assert np.array_equal(bias1, bias2)