With 50% prob, negate the value

Build a module from config dict. Args: cfg (dict): Config dict. It should at least contain the key "type". registry (:obj:`Regist

Builds loss function with specific configuration. Args: config: the configuration. Returns: A nn.Module loss.

Converts all `BatchNorm2d` and `SyncBatchNorm` layers of provided module into `FrozenBatchNorm2d`. If `module` is itself an instance of eithe

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

NMS for multi-class bboxes. Args: multi_bboxes (Tensor): shape (n, #class*4) or (n, 4) multi_scores (Tensor): shape (n, #class)

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

Convert objects of various python types to :obj:`torch.Tensor`. Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`, :class:`S

Apply element-wise weight and reduce loss. Args: loss (Tensor): Element-wise loss. weight (Tensor): Element-wise weights.

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Creates a mnasnet-a1 model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet Paper: https://arxiv.org/pdf/1807

Creates a mnasnet-b1 model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet Paper: https://arxiv.org/pdf/1807

Generate MobileNet-V2 network Ref impl: https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet_v2.py Paper:

initialize conv/fc bias value according to giving probablity

Calculate a proportional bbox region. The bbox center are fixed and the new h' and w' is h * ratio and w * ratio. Args: bbox (Tensor

Calculate recalls. Args: gts (list[ndarray]): a list of arrays of shape (n, 4) proposals (list[ndarray]): a list of arrays of sha

Flip Tensor along a dimension

Applies the flow color wheel to (possibly clipped) flow components u and v. According to the C++ source code of Daniel Scharstein Accordi

Get the root logger. The logger will be initialized if it has not been initialized. By default a StreamHandler will be added. If `log_file` i

Convert targets by image to targets by feature level. [target_img0, target_img1] -> [target_level0, target_level1, ...]

Read an image. Args: img_or_path (ndarray or str): Either a numpy array or image path. If it is a numpy array (loaded image),

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

Old style model is stored with all names of parameters share common prefix 'module.'

Saves the given label to image on disk. Args: label: The numpy array to be saved. The data will be converted to uint8 and save