Update statistics

Creates an EfficientNet model. Ref impl: https://github.com/tensorflow/tpu/blob/master/models/official/efficientnet/efficientnet_model.py Pap

r"""Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distributi

Convert a list of bboxes to roi format. Args: bbox_list (list[Tensor]): a list of bboxes corresponding to a batch of images.

Update statistics

Build convolution layer Args: cfg (None or dict): cfg should contain: type (str): identify conv layer type. laye

Read the next frame. If the next frame have been decoded before and in the cache, then return it directly, otherwise decode, cache an

Build normalization layer Args: cfg (dict): cfg should contain: type (str): identify norm layer type. layer args

Computes the precision@k for the specified values of k

Create configs and perform basic setups.

Load checkpoint from a file or URI. Args: model (Module): Module to load checkpoint. filename (str): Either a filepath or URL or

Register a hook into the hook list. Args: hook (:obj:`Hook`): The hook to be registered. priority (int or str or :obj

Whether the input is an string instance.

Args: pool_type: 'max' or 'avg'

Creates an EfficientNet-Lite model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite Paper: https://

- Inputs grad_output: float32 (B, H, L_query, L_key) - Outputs grad_input: float32 (B, H, L_query, nu

Calculate the ious between each bbox of bboxes1 and bboxes2. Args: bboxes1(ndarray): shape (n, 4) bboxes2(ndarray): shape (k, 4)

Get the config of relative position encoding on queries, keys and values Parameters ---------- ratio: float The ratio to control

Random select some elements from the gallery. It seems that Pytorch's implementation is slower than numpy so we use numpy to randperm