r""" Sets the epoch for this sampler. When :attr:`shuffle=True`, this ensures all replicas use a different random ordering for each ep

assuming input size 8x8 or 16x16

assuming input size 8x8 or 16x16

Returns: str: module name of the caller tuple: a hashable key to be used to identify different callers

Gets files for the specified data type and dataset split. Args: data: String, desired data ('image' or 'label'). datas

Gets files for the specified data type and dataset split. Args: data: String, desired data ('image' or 'label'). datas

Return the learning rate warmup factor at a specific iteration. See https://arxiv.org/abs/1706.02677 for more details. Args: meth

This function is taken from the original tf repo. It ensures that all layers have a channel number that is divisible by 8 It can be seen

Compute regression and classification targets for anchors. Args: anchor_list (list[list]): Multi level anchors of each image. val

Return configs as markdown format

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

Map bboxes from the original image scale to testing scale

Build head model from config dict.

1x1 convolution

3x3 convolution with padding

3x3 convolution with padding

Convert a video with ffmpeg. This provides a general api to ffmpeg, the executed command is:: `ffmpeg -y <pre_options> -i <in_file> <opt

Select a 2d convolution implementation based on arguments Creates and returns one of torch.nn.Conv2d, Conv2dSame, MixedConv2d, or CondConv2d.

Decode distance prediction to bounding box. Args: points (Tensor): Shape (n, 2), [x, y]. distance (Tensor): Distance from the giv

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). This is the same as the DropConnect impl I created for E

Evaluate mAP of a dataset. Args: det_results (list[list]): [[cls1_det, cls2_det, ...], ...]. The outer list indicates images,

Feature Channel Shortcut Returns feature channel count for each output index if idx == None. If idx is an integer, will return featur

Get class names of a dataset.

Get a yacs CfgNode object with default values.

Make python logger

Get the config of single relative position encoding Parameters ---------- ratio: float The ratio to control the number of buckets

Get the config of single relative position encoding Parameters ---------- ratio: float The ratio to control the number of buckets

Get the config of single relative position encoding Parameters ---------- ratio: float The ratio to control the number of buckets