Get a block through a string notation of arguments. Args: block_string (str): A string notation of arguments.

Encode a block to a string. Args: block (namedtuple): A BlockArgs type argument. Returns: block_string: A Stri

Each extension will be treated with particular extension loader

Currenly, Using Glob for loading file with regex It might be changed for better performance in large datasets

This function apply the affine transform to each point given by an affine matrix

Override to build the mask

Decode a list of string notations to specify blocks inside the network. Args: string_list (list[str]): A list of strings, each str

Drop connect. Args: input (tensor: BCWH): Input of this structure. p (float: 0.0~1.0): Probability of drop connection. tra

Create BlockArgs and GlobalParams for efficientnet model. Args: width_coefficient (float) depth_coefficient (float) image_

Use convolution layer to extract features from reduction levels i in [1, 2, 3, 4, 5]. Args: inputs (tensor): Input tensor.

This func to freeze some specific layers to warm up the models

Create an efficientnet model according to name. Args: model_name (str): Name for efficientnet. in_channels (int): Inpu

Return a list of the available masks for cli

Obtain height and width from x. Args: x (int, tuple or list): Data size. Returns: size: A tuple or list (H,W).

Infer the scope of registry. The name of the package where registry is defined will be returned. Example: >>> # in mmdet/m

Loads pretrained weights from weights path or download using url. Args: model (Module): The whole model of efficientnet. model_nam

Return the mask in requested shape

Calculate module's repeat number of a block based on depth multiplier. Use depth_coefficient of global_params. Args: repeats (int):

Sets swish function as memory efficient (for training) or standard (for export). Args: memory_efficient (bool): Whether to use mem

Split scope and key. The first scope will be split from key. Examples: >>> Registry.split_scope_key('mmdet.ResNet')

This func to unfreeze all model layers