Get the stage id to set the different learning rates in ``stage_wise`` decay_type. Args: var_name (str): The key of the model.

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

Calculate the ground truth for all samples in a batch according to the sampling_results. Almost the same as the implementation in bbo

Compute regression and classification targets for anchors in multiple images. Args: anchor_list (list[list[Tensor]]): Mul

Calculate the ground truth for all samples in a batch according to the sampling_results. Almost the same as the implementation in bbo

Calculate the ground truth for all samples in a batch according to the sampling_results. Args: sampling_results (List[obj

Convert ground truth to coco format json file. Args: gt_dicts (Sequence[dict]): Ground truth of the dataset. outfile_

Hue distortion. Args: img (np.ndarray): The input image. Returns: np.ndarray: Image after hue change.

Calculate Intersection and Union. Args: pred_label (torch.tensor): Prediction segmentation map or predict result

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

Load image :param imgPath: path of the image to load :return: numpy array of the image

Load image :param imgPath: path of the image to load :return: numpy array of the image

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

Load proposals from proposals file. The `proposals_list` should be a dict[img_path: proposals] with the same length as `data_list`. A

Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``F

Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``F

Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``F

Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``F

Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``F

Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``F

Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``F

Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``F

Calculate the loss based on the network predictions and targets. Args: cls_score (Tensor): Classification prediction

Calculate losses from a batch of inputs and data samples.

Calculate the loss based on the network predictions and targets. Args: cls_score (Tensor): Classification prediction

Calculate the loss based on the features extracted by the detection head. Args: cls_scores (list[Tensor]): Box scores for

Perform forward propagation and loss calculation of the mask head on the features of the upstream network. Args: x (tuple

Merging patch bboxes into full image. Args: results (list): Testing results of the dataset. nproc (int): number of pr

Merging patch bboxes into full image. Args: results (list): Testing results of the dataset. nproc (int): number of pr

Merge patches' predictions into full image's results and generate a zip file for DOTA online evaluation. You can submit it at:

Pad gt_masks to shape of batch_input_shape.

Pad gt_sem_seg to shape of batch_input_shape.

Parse raw annotation to target format. Args: raw_data_info (dict): Raw data information load from ``ann_file`` Returns:

Parse raw annotation to target format. Args: raw_data_info (dict): Raw data information load from ``ann_file`` Returns:

Parse raw annotation to target format. Args: img_info (dict): Raw image information, usually it includes `img_id`

Monkey-patch an existing `DataParallel` object. Add the replication callback. Useful when you have customized `DataParallel` implementation.

Predict results from a batch of inputs and data samples with post- processing. Args: batch_inputs (Tensor): Inputs with s

Predict results from a batch of inputs and data samples with post- processing.

Perform forward propagation of the detection head and predict detection results on the features of the upstream network. Args:

Predict results from a batch of inputs and data samples with post- processing. Args: inputs (Tensor): Inputs with shape (

Predict results from a batch of inputs and data samples with post- processing. Args: batch_inputs (Tensor): Inputs with s

Perform forward propagation of the detection head and predict detection results on the features of the upstream network. Args:

Perform forward propagation of the bbox head and predict detection results on the features of the upstream network. Args:

Perform forward propagation of the mask head and predict detection results on the features of the upstream network. Args:

Print mAP and results of each class. A table will be printed to show the gts/dets/recall/AP of each class and the mAP. Args: mea

Forward function of PSP module.

Register an slave device. Args: identifier: an identifier, usually is the device id. Returns: a `SlavePipe` obj

Regress the bbox for the predicted class. Used in Cascade R-CNN. Args: priors (Tensor): Priors from `rpn_head` or last stage

Regress the bbox for the predicted class. Used in Cascade R-CNN. Args: priors (Tensor): Priors from `rpn_head` or last stage