Initialize a Linear or Convolutional layer.

Initialize a Batchnorm layer.

Args: x: (batch_size , ...) mixup_lambda: (batch_size,) Returns: out: (batch_size, ...)

Interpolate data in time domain. This is used to compensate the resolution reduction in downsampling of a CNN. Args: x: (batch_siz

Pad framewise_output to the same length as input frames. The pad value is the same as the value of the last frame. Args: framewise_out

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

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

Combine all balanced and unbalanced indexes hdf5s to a single hdf5. This combined indexes hdf5 is used for training with full data (~20k balanced

Create indexes a for dataloader to read for training. When users have a new task and their own data, they need to create similar indexes. The

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 Ef

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

Load waveform and target of an audio clip. Args: index: the index number Return: { "hdf5_path": str,

Load waveform and target of an audio clip. Args: index: the index number Return: { "audio_name": str,

Load waveform and target of an audio clip. Args: index: the index number Return: { "audio_name": str,