def test_normalize_dense_matrix_enum(self):
normalization_parameters = {
'f1':
NormalizationParameters(identify_types.ENUM, None, None, None,
None, [12.0, 4.2, 2.1]),
'f2':
NormalizationParameters(identify_types.CONTINUOUS, None, 0, 0, 1,
None),
'f3':
NormalizationParameters(identify_types.ENUM, None, None, None,
None, [15.1, -3.2])
}
features = list(normalization_parameters.keys())
norm_net = core.Net("net")
blobname_template = '{}_blob'
blob_map = prepare_normalization(norm_net, normalization_parameters,
features, blobname_template, False)
inputs = np.array(
[[12.0, 1.0, 15.1], [4.2, 2.0, -3.2], [2.1, 3.0, 15.1],
[2.1, 3.0, normalization.MISSING_VALUE]],
dtype=np.float32)
normalized_outputs = normalize_dense_matrix(inputs, features,
normalization_parameters,
blob_map, norm_net,
blobname_template)
np.testing.assert_array_equal(
np.array([
[1, 0, 0, 1.0, 1, 0],
[0, 1, 0, 2.0, 0, 1],
[0, 0, 1, 3.0, 1, 0],
[0, 0, 1, 3.0, 0, 0] # Missing values should go to all 0
]),
normalized_outputs)
def _normalize_actions(self, actions: np.ndarray) -> np.ndarray:
if self.skip_normalization:
return actions
return normalize_dense_matrix(actions, self._action_features,
self._action_normalization_parameters,
self.action_norm_blobs,
self.action_norm_net,
self.action_norm_blobname_template,
self.num_action_features)
def _normalize_states(self, states: np.ndarray) -> np.ndarray:
"""
Normalizes input states and replaces NaNs with 0. Returns a matrix of
the same shape. Make sure to have set up the underlying normalization net
with `_prepare_state_normalization`.
:param states: Numpy array with shape (batch_size, state_dim) containing
raw state inputs
"""
if self.skip_normalization:
return states
return normalize_dense_matrix(
states, self._state_features, self._state_normalization_parameters,
self.state_norm_blobs, self.state_norm_net,
self.state_norm_blobname_template, self.num_state_features
)
