garage.misc.tensor_utils module¶
Utiliy functions for tensors.
-
concat_tensor_dict_list
(tensor_dict_list)[source]¶ Concatenate dictionary of list of tensor.
Parameters: tensor_dict_list (dict[list]) – a list of dictionaries of {tensors or dictionary of tensors}. Returns: - a dictionary of {stacked tensors or dictionary of
- stacked tensors}
Return type: dict
-
discount_cumsum
(x, discount)[source]¶ Discounted cumulative sum.
See https://docs.scipy.org/doc/scipy/reference/tutorial/signal.html#difference-equation-filtering # noqa: E501 Here, we have y[t] - discount*y[t+1] = x[t] or rev(y)[t] - discount*rev(y)[t-1] = rev(x)[t]
Parameters: - x (np.ndarrary) – Input.
- discount (float) – Discount factor.
Returns: Discounted cumulative sum.
Return type:
-
explained_variance_1d
(ypred, y)[source]¶ Explained variation for 1D inputs.
It is the proportion of the variance in one variable that is explained or predicted from another variable.
Parameters: - ypred (np.ndarray) – Sample data from the first variable.
- y (np.ndarray) – Sample data from the second variable.
Returns: The explained variance.
Return type:
-
flatten_tensors
(tensors)[source]¶ Flatten a list of tensors.
Parameters: tensors (list[numpy.ndarray]) – List of tensors to be flattened. Returns: Flattened tensors. Return type: numpy.ndarray
-
normalize_pixel_batch
(env_spec, observations)[source]¶ Normalize the observations (images).
If the input are images, it normalized into range [0, 1].
Parameters: - env_spec (garage.envs.EnvSpec) – Environment specification.
- observations (numpy.ndarray) – Observations from environment.
Returns: Normalized observations.
Return type: numpy.ndarray
-
pad_tensor
(x, max_len, mode='zero')[source]¶ Pad tensors.
Parameters: Returns: Padded tensor.
Return type: numpy.ndarray
-
pad_tensor_dict
(tensor_dict, max_len, mode='zero')[source]¶ Pad dictionary of tensors.
Parameters: Returns: Padded tensor.
Return type: dict[numpy.ndarray]
-
pad_tensor_n
(xs, max_len)[source]¶ Pad array of tensors.
Parameters: - xs (numpy.ndarray) – Tensors to be padded.
- max_len (int) – Maximum length.
Returns: Padded tensor.
Return type: numpy.ndarray
-
split_tensor_dict_list
(tensor_dict)[source]¶ Split dictionary of list of tensor.
Parameters: tensor_dict (dict[numpy.ndarray]) – a dictionary of {tensors or dictionary of tensors}. Returns: - a dictionary of {stacked tensors or dictionary of
- stacked tensors}
Return type: dict
-
stack_tensor_dict_list
(tensor_dict_list)[source]¶ Stack a list of dictionaries of {tensors or dictionary of tensors}.
Parameters: tensor_dict_list (dict[list]) – a list of dictionaries of {tensors or dictionary of tensors}. Returns: - a dictionary of {stacked tensors or dictionary of
- stacked tensors}
Return type: dict