lerobot/common/policies/normalize.py [119:171]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(
        self,
        features: dict[str, PolicyFeature],
        norm_map: dict[str, NormalizationMode],
        stats: dict[str, dict[str, Tensor]] | None = None,
    ):
        """
        Args:
            shapes (dict): A dictionary where keys are input modalities (e.g. "observation.image") and values
            are their shapes (e.g. `[3,96,96]`]). These shapes are used to create the tensor buffer containing
            mean, std, min, max statistics. If the provided `shapes` contain keys related to images, the shape
            is adjusted to be invariant to height and width, assuming a channel-first (c, h, w) format.
            modes (dict): A dictionary where keys are output modalities (e.g. "observation.image") and values
                are their normalization modes among:
                    - "mean_std": subtract the mean and divide by standard deviation.
                    - "min_max": map to [-1, 1] range.
            stats (dict, optional): A dictionary where keys are output modalities (e.g. "observation.image")
                and values are dictionaries of statistic types and their values (e.g.
                `{"mean": torch.randn(3,1,1)}, "std": torch.randn(3,1,1)}`). If provided, as expected for
                training the model for the first time, these statistics will overwrite the default buffers. If
                not provided, as expected for finetuning or evaluation, the default buffers should to be
                overwritten by a call to `policy.load_state_dict(state_dict)`. That way, initializing the
                dataset is not needed to get the stats, since they are already in the policy state_dict.
        """
        super().__init__()
        self.features = features
        self.norm_map = norm_map
        self.stats = stats
        stats_buffers = create_stats_buffers(features, norm_map, stats)
        for key, buffer in stats_buffers.items():
            setattr(self, "buffer_" + key.replace(".", "_"), buffer)

    # TODO(rcadene): should we remove torch.no_grad?
    @torch.no_grad
    def forward(self, batch: dict[str, Tensor]) -> dict[str, Tensor]:
        # TODO: Remove this shallow copy
        batch = dict(batch)  # shallow copy avoids mutating the input batch
        for key, ft in self.features.items():
            if key not in batch:
                # FIXME(aliberts, rcadene): This might lead to silent fail!
                continue

            norm_mode = self.norm_map.get(ft.type, NormalizationMode.IDENTITY)
            if norm_mode is NormalizationMode.IDENTITY:
                continue

            buffer = getattr(self, "buffer_" + key.replace(".", "_"))

            if norm_mode is NormalizationMode.MEAN_STD:
                mean = buffer["mean"]
                std = buffer["std"]
                assert not torch.isinf(mean).any(), _no_stats_error_str("mean")
                assert not torch.isinf(std).any(), _no_stats_error_str("std")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



lerobot/common/policies/normalize.py [193:244]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(
        self,
        features: dict[str, PolicyFeature],
        norm_map: dict[str, NormalizationMode],
        stats: dict[str, dict[str, Tensor]] | None = None,
    ):
        """
        Args:
            shapes (dict): A dictionary where keys are input modalities (e.g. "observation.image") and values
            are their shapes (e.g. `[3,96,96]`]). These shapes are used to create the tensor buffer containing
            mean, std, min, max statistics. If the provided `shapes` contain keys related to images, the shape
            is adjusted to be invariant to height and width, assuming a channel-first (c, h, w) format.
            modes (dict): A dictionary where keys are output modalities (e.g. "observation.image") and values
                are their normalization modes among:
                    - "mean_std": subtract the mean and divide by standard deviation.
                    - "min_max": map to [-1, 1] range.
            stats (dict, optional): A dictionary where keys are output modalities (e.g. "observation.image")
                and values are dictionaries of statistic types and their values (e.g.
                `{"mean": torch.randn(3,1,1)}, "std": torch.randn(3,1,1)}`). If provided, as expected for
                training the model for the first time, these statistics will overwrite the default buffers. If
                not provided, as expected for finetuning or evaluation, the default buffers should to be
                overwritten by a call to `policy.load_state_dict(state_dict)`. That way, initializing the
                dataset is not needed to get the stats, since they are already in the policy state_dict.
        """
        super().__init__()
        self.features = features
        self.norm_map = norm_map
        self.stats = stats
        # `self.buffer_observation_state["mean"]` contains `torch.tensor(state_dim)`
        stats_buffers = create_stats_buffers(features, norm_map, stats)
        for key, buffer in stats_buffers.items():
            setattr(self, "buffer_" + key.replace(".", "_"), buffer)

    # TODO(rcadene): should we remove torch.no_grad?
    @torch.no_grad
    def forward(self, batch: dict[str, Tensor]) -> dict[str, Tensor]:
        batch = dict(batch)  # shallow copy avoids mutating the input batch
        for key, ft in self.features.items():
            if key not in batch:
                continue

            norm_mode = self.norm_map.get(ft.type, NormalizationMode.IDENTITY)
            if norm_mode is NormalizationMode.IDENTITY:
                continue

            buffer = getattr(self, "buffer_" + key.replace(".", "_"))

            if norm_mode is NormalizationMode.MEAN_STD:
                mean = buffer["mean"]
                std = buffer["std"]
                assert not torch.isinf(mean).any(), _no_stats_error_str("mean")
                assert not torch.isinf(std).any(), _no_stats_error_str("std")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -