Check input folder or file. Args: input_path (str): input folder or file path. allowed_suffix (List[str], optional):

Build a runner from config. Args: cfg (ConfigType): A config used for building runner. Keys of ``cfg`` can see :m

Get a numpy of colors of shape (N, 3).

Whether the input is an string instance. Note: This method is deprecated since python 2 is no longer supported.

Load checkpoint from given ``filename``. Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Helper function to convert all `SyncBatchNorm` (SyncBN) and `mmcv.ops.sync_bn.SyncBatchNorm`(MMSyncBN) layers in the model to `BatchNormXd` la

Extract a multi-scale single image tensor from a multi-scale batch tensor based on batch index. Note: The default value of detach is True, be

Build a module from config dict and wrap module with "wrapper_func". Args: cfg (dict): Config dict. It should at least contain the key "t

Decode the keypoint coordinates from heatmaps and displacements. The decoded keypoint coordinates are in the input image space. Args:

Check if a module is a module wrapper. The following 3 modules in MMCV (and their subclasses) are regarded as module wrappers: DataParallel,

Returns: iterator: An iterator object whose element is (key, value) tuple pairs for ``data``.

Perform orthographic projection of 3D points using the camera parameters, return projected 2D points in image plane. Notes: batch siz

Return intersection-over-union (Jaccard index) of boxes. Both sets of boxes are expected to be in (x_center, y_center, width, height, angle)

Recursively convert Tensor in inputs from src_type to dst_type. Note: In v1.4.4 and later, ``cast_tersor_type`` will only convert the

Returns the currently existing device type. Returns: str: cuda | npu | mlu | mps | cpu.

Get keypoint index from specified convention with keypoint name. Args: name (str): keypoint name convention (str): data type from

Infer a suitable file client based on the URI and arguments. Args: file_client_args (dict, optional): Arguments to instantiate a

Inverse function of sigmoid. Args: x (Tensor): The tensor to do the inverse. eps (float): EPS avoid numerical overflow. Defaults

Calculate the loss based on the features extracted by the DIIHead. Args: cls_score (Tensor): Classification prediction

Dispatch to either CPU or GPU NMS implementations. The input can be either torch tensor or numpy array. GPU NMS will be used if the input is

Check output folder or file. Args: output_path (str): could be folder or file. allowed_suffix (List[str], optional):

Save checkpoint to file. The checkpoint will have 3 fields: ``meta``, ``state_dict`` and ``optimizer``. By default ``meta`` will contain vers

Assign dataset_meta to the visualizer. The default visualization settings will be overridden. Args: dataset_meta (dict):

Special method for set union field, used as property.setter functions.

Change the device of the data inplace. Example: >>> self = SamplingResult.random() >>> print(f'self = {self.to(None)}

Handle predicted instances when RoI is empty. Note: If ``instance_results`` is not None, it will be modified in place internally, and then re

Get annotation by index. Args: idx (int): Global index of ``ConcatDataset``. Returns: dict: The idx-th annot

Get targets for PAA head. This method is almost the same as `AnchorHead.get_targets()`. We direct return the results from _get_target

Calculate the pose accuracy of PCK for each individual keypoint and the averaged accuracy across all keypoints for coordinates. Note:

Loads log scalars, runtime information and resumed keys from ``state_dict`` or ``message_hub``. If ``state_dict`` is a dictionary ret

Apply element-wise weight and reduce loss. Args: loss (Tensor): Element-wise loss. weight (Optional[Tensor], optional): Element-w

Convert a ``filepath`` to standard format of petrel oss. If the ``filepath`` is concatenated by ``os.path.join``, in a Windows enviro

Map ``filepath`` to a string path whose prefix will be replaced by :attr:`self.path_mapping`. Args: filepath (str or Path

Cauculate mean per joint position error (MPJPE) or its variants PA- MPJPE. Report mean per joint position error (MPJPE) and mean per

Obtain bbox in xywh format given bbox in xyxy format Args: bbox_xyxy (List[float]): Bounding box in xyxy format Returns:

Convert axis_angle to rotation matrixs. Args: axis_angle (Union[torch.Tensor, numpy.ndarray]): input shape should be

r"""Performs non-maximum suppression in a batched fashion. Modified from `torchvision/ops/boxes.py#L39 <https://github.com/pytorch/vision/blo

Convert bbox coordinates from (x1, y1, x2, y2) to (cx, cy, w, h). Args: bbox (Tensor): Shape (n, 4) for bboxes. Returns: Ten

Build body_models.

Build a module from config dict when it is a class configuration, or call a function from config dict when it is a function configuration. If

Check input folder or file. Args: input_path (str): input folder or file path. allowed_suffix (List[str], optional):

Read bytes from a given ``filepath`` with 'rb' mode. Args: filepath (str or Path): Path to read data. backend_args (dict, optiona

Get raw value from the dict. It acts the same as dict.__getitem__(k). Args: key (_KT): Key in dict.

Get the shapes from a jit value object. Args: val (torch._C.Value): jit value object. Returns: list(int): return a list of i

Check whether it is a tuple of some type. A partial method of :func:`is_seq_of`.

nn.Module: the normalization layer named "norm1"

nn.Module: normalization layer after the second convolution layer

Create random AssignResult for tests or debugging. Args: num_preds: number of predicted boxes num_gts: number of true

Randomly disable the transform.

Show the drawn image. Args: drawn_img (np.ndarray, optional): The image to show. If drawn_img is None, it will sh

get config text.

Overrides this method to call :meth:`BaseDataPreprocessor.to` additionally. Returns: nn.Module: The model itself.

A helper function to ensure body model parameters have the same batch size as the input keypoints. Args: init_param: inpu

A helper function to ensure body model parameters have the same batch size as the input keypoints. Args: init_param: inpu

Cauculate the Area Under the Curve (AUC) computed for a range of 3DPCK thresholds. Args: keypoint_results (list): Keypoint

Cauculate Percentage of Correct Keypoints (3DPCK) w. or w/o Procrustes alignment. Args: keypoint_results (list): Keypoint

Cauculate per vertex error.

Attention function.

Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataload

Returns the image size, if provided, expected in the form of (height, width) The image size is used for conversion of projected points

Returns the image size, if provided, expected in the form of (height, width) The image size is used for conversion of projected points

r"""Initialize a module. Args: module (``torch.nn.Module``): the module will be initialized. init_cfg (dict | list[dict]): initia

Calculate the dist matrixes for loss measurement. Args: key_embeds (Tensor): Embeds of positive bboxes in sampling results

Randomly negative the value.

Set the image to draw. Args: image (np.ndarray): The image to draw. backend (str): The backend to save the image.

Set requires_grad and collect parameters for optimization. Args: fit_param: whether to optimize this body model parameter

Set requires_grad and collect parameters for optimization. Args: fit_param: whether to optimize this body model parameter

Set ``pred_label``.

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Unpacks data for :meth:`forward` Args: data (dict or tuple or list): Data sampled from dataset. mode (str): Mode of f

Record the image. Args: name (str): The image identifier. image (np.ndarray, optional): The image to be saved. The fo

Copying data to the target device. Args: data (dict): Data returned by ``DataLoader``. Returns: CollatedResu

Parse dictionary to ipu options. Args: cfg (dict): A dictionary of ipu settings. Returns: dict[str, poptorch.Options]: Train