releso.feature_extractor.CombinedExtractor

class releso.feature_extractor.CombinedExtractor(observation_space: gymnasium.spaces.Dict, cnn_output_dim: int = 256, without_linear: bool = False, network_type: Literal['resnet18', 'mobilenetv2'] = 'resnet18', logger: Logger | None = None)

Bases: BaseFeaturesExtractor

Combined Extractor can use a Dict definition of the observations space.

Notes: Class is a direct copy from

stable_baselines3.common.torch_layers.CombinedExtractor. Only change is the image feature extractor.

__init__(observation_space: gymnasium.spaces.Dict, cnn_output_dim: int = 256, without_linear: bool = False, network_type: Literal['resnet18', 'mobilenetv2'] = 'resnet18', logger: Logger | None = None)

Combined Feature extractor constructor.

The feature extractor is used to also be able to handle image based observations better and to give the option to used pretrained networks as the feature extractor. Multiple are available please look into the code to check the currently available pretrained networks. Not all are listed in the network_type variable hint.

The combined feature extractor extends this capability to non uniform observations space definitions. For example if image based observations are mixed with standard (scalar) observations. Or multiple images are used as an observation.

Parameters:

  • observation_space (spaces.Dict) – Observations space of the

  • environment.

  • cnn_output_dim (int, optional) – How many features the feature

  • 256. (extractor should return. Defaults to)

  • without_linear (bool, optional) – Use the pretrained nets without a

  • possible (linear layer at the end. Setting the output_dim is not)

  • size. (since the output is directly dependent on the input)

  • False. (Defaults to)

  • network_type (Literal["resnet18", "mobilenetv2"],optional) – Network

  • "resnet18". (to use for the cnn extractor. Defaults to)

  • logger (Optional[logging.Logger], optional) – Logger to use for

  • None. (logging purposes. Defaults to)

Methods

add_module(name, module)

Add a child module to the current module.

apply(fn)

Apply fn recursively to every submodule (as returned by .children()) as well as self.

bfloat16()

Casts all floating point parameters and buffers to bfloat16 datatype.

buffers([recurse])

Return an iterator over module buffers.

children()

Return an iterator over immediate children modules.

compile(*args, **kwargs)

Compile this Module's forward using torch.compile().

cpu()

Move all model parameters and buffers to the CPU.

cuda([device])

Move all model parameters and buffers to the GPU.

double()

Casts all floating point parameters and buffers to double datatype.

eval()

Set the module in evaluation mode.

extra_repr()

Return the extra representation of the module.

float()

Casts all floating point parameters and buffers to float datatype.

forward(observations)

Forward pass of the Network defined.

get_buffer(target)

Return the buffer given by target if it exists, otherwise throw an error.

get_extra_state()

Return any extra state to include in the module's state_dict.

get_parameter(target)

Return the parameter given by target if it exists, otherwise throw an error.

get_submodule(target)

Return the submodule given by target if it exists, otherwise throw an error.

half()

Casts all floating point parameters and buffers to half datatype.

ipu([device])

Move all model parameters and buffers to the IPU.

load_state_dict(state_dict[, strict, assign])

Copy parameters and buffers from state_dict into this module and its descendants.

modules()

Return an iterator over all modules in the network.

mtia([device])

Move all model parameters and buffers to the MTIA.

named_buffers([prefix, recurse, ...])

Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.

named_children()

Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.

named_modules([memo, prefix, remove_duplicate])

Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.

named_parameters([prefix, recurse, ...])

Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.

parameters([recurse])

Return an iterator over module parameters.

register_backward_hook(hook)

Register a backward hook on the module.

register_buffer(name, tensor[, persistent])

Add a buffer to the module.

register_forward_hook(hook, *[, prepend, ...])

Register a forward hook on the module.

register_forward_pre_hook(hook, *[, ...])

Register a forward pre-hook on the module.

register_full_backward_hook(hook[, prepend])

Register a backward hook on the module.

register_full_backward_pre_hook(hook[, prepend])

Register a backward pre-hook on the module.

register_load_state_dict_post_hook(hook)

Register a post-hook to be run after module's load_state_dict() is called.

register_load_state_dict_pre_hook(hook)

Register a pre-hook to be run before module's load_state_dict() is called.

register_module(name, module)

Alias for add_module().

register_parameter(name, param)

Add a parameter to the module.

register_state_dict_post_hook(hook)

Register a post-hook for the state_dict() method.

register_state_dict_pre_hook(hook)

Register a pre-hook for the state_dict() method.

requires_grad_([requires_grad])

Change if autograd should record operations on parameters in this module.

set_extra_state(state)

Set extra state contained in the loaded state_dict.

set_submodule(target, module[, strict])

Set the submodule given by target if it exists, otherwise throw an error.

share_memory()

See torch.Tensor.share_memory_().

state_dict(*args[, destination, prefix, ...])

Return a dictionary containing references to the whole state of the module.

to(*args, **kwargs)

Move and/or cast the parameters and buffers.

to_empty(*, device[, recurse])

Move the parameters and buffers to the specified device without copying storage.

train([mode])

Set the module in training mode.

type(dst_type)

Casts all parameters and buffers to dst_type.

xpu([device])

Move all model parameters and buffers to the XPU.

zero_grad([set_to_none])

Reset gradients of all model parameters.

Attributes

T_destination

call_super_init

dump_patches

features_dim

The number of features that the extractor outputs.

training

forward(observations: dict[str, Tensor]) → Tensor

Forward pass of the Network defined.

Parameters:

observations (th.Tensor) – Input for the network

Returns:

Output of the network

Return type:

th.Tensor