Calls either forward_train or forward_test depending on whether return_loss=True. Note this setting will change the expected inputs.

Args: x (Torch.Tensor): Feature map output by Fuser. (B, C, H, W)

Forward function.

Forward function.

Forward function. Args: pred (torch.Tensor): The prediction. target (torch.Tensor): The learning target of the predic

features (dict): Features output by encoders - "stream1": Torch.tensor, B,C,H,W - ...

features (dict): Features output by encoders - "stream1": Torch.tensor, B,C,H,W - ...

Forward function for training when knowledge distillation. Returns: loss_dict (dict) [optional]: loss of original head loss

Get category distribution of single scene. Args: idx (int): Index of the data_info. Returns: dict[list]: for

Load annotations from ann_file. Args: ann_file (str): Path of the annotation file. Returns: list[dict]: List

Training data preparation. Args: index (int): Index for accessing the target data. Returns: dict: Training d

Training data preparation. Args: index (int): Index for accessing the target data. Returns: dict: Training d

Convert the model into training mode while keep normalization layer freezed.

The iteration step during training. This method defines an iteration step during training, except for the back propagation and optimi

The iteration step during validation. This method shares the same signature as :func:`train_step`, but used during val epochs. Note t