:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])

:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])

:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])

features: [N, T, ...] (assume the second dimension represents length) lens: [N,]

Applies the preprocessing operations used in training the Speaker Encoder to a waveform either on disk or in memory. The waveform will be re

Read hdf5 dataset. Args: hdf5_name (str): Filename of hdf5 file. hdf5_path (str): Dataset name in hdf5 file. Return:

Remove weight normalization module from all of the layers.

Perform STFT and convert to magnitude spectrogram. Args: x (Tensor): Input signal tensor (B, T). fft_size (int): FFT size.

Initialize Conv2d module.

Initialize STFT loss module.

r"""Process audio and/or text per batch

r"""Process audio and/or text per batch

:param dur_input: [B, T_txt, H] :param mel2ph: [B, T_mel] :param txt_tokens: [B, T_txt] :param ret: :return:

:param dur_pred: [B, T], float, log scale :param mel2ph: [B, T] :param txt_tokens: [B, T] :param losses: :ret

Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas

Find contiguous regions from bool valued numpy.array. Copy of https://dcase-repo.github.io/dcase_util/_modules/dcase_util/data/decisions.html#Deci

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

python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte

python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte

Helper for getting incremental state for an nn.Module.

r"""Load list of class labels and return text embeddings

Initialize a Batchnorm layer.

Initialize a Batchnorm layer.

Initialize a Linear or Convolutional layer.

features: [N, T, ...] (assume the second dimension represents length) lens: [N,]

Take the mean over all non-batch dimensions.