PixelCNN¶
-
class
torchelie.models.PixelCNN(hid: int, sz: Tuple[int, int], channels: int = 3, n_layer: int = 3)¶ A PixelCNN model with 6 blocks
- Parameters
hid (int) – the number of hidden channels in the blocks
sz ((int, int)) – the size of the images to learn. Must be square
channels (int) – number of channels in the data. 3 for RGB images
-
forward(x: torch.Tensor) → torch.Tensor¶ A forward pass for training
-
partial_sample(x: torch.Tensor, temp: float) → torch.Tensor¶
-
sample(temp: float, N: int) → torch.Tensor¶ Sample a batch of images
- Parameters
temp (float) – the sampling temperature
N (int) – number of images to generate in the batch
- Returns
A batch of images
-
sample_(img: torch.Tensor, temp: float = 0, start_coord: Tuple[int, int] = (0, 0)) → torch.Tensor¶
-
sample_cond(cond: torch.Tensor, temp: float) → torch.Tensor¶
-
training: bool¶