VQ¶
-
class
torchelie.nn.
VQ
(latent_dim: int, num_tokens: int, dim: int = 1, commitment: float = 0.25, init_mode: str = 'normal', return_indices: bool = True, max_age: int = 1000)¶ Quantization layer from Neural Discrete Representation Learning
- Parameters
latent_dim (int) – number of features along which to quantize
num_tokens (int) – number of tokens in the codebook
dim (int) – dimension along which to quantize
return_indices (bool) – whether to return the indices of the quantized code points
-
forward
(x: torch.Tensor) → Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]]¶ Forward pass
- Parameters
x (tensor) – input tensor
- Returns
quantized tensor, or (quantized tensor, indices) if self.return_indices
-
resample_dead
(x)¶
-
update_usage
(indices)¶
-
commitment
: float¶
-
dim
: int¶
-
embedding
: torch.nn.modules.sparse.Embedding¶
-
init_mode
: str¶
-
initialized
: torch.Tensor¶
-
return_indices
: bool¶