Convert a batch of tensors to their original scale. Args: batch (torch.Tensor): Batch of normalized tensors. mean (torch.Tensor or list): Mean used for normalization. std (torch.Tensor or list): Standard deviation used for normalization. Returns: torch.
(batch, mean=[0.1307], std=[0.3081])
| 225 | |
| 226 | # restores the tensors to their original scale |
| 227 | def denorm(batch, mean=[0.1307], std=[0.3081]): |
| 228 | """ |
| 229 | Convert a batch of tensors to their original scale. |
| 230 | |
| 231 | Args: |
| 232 | batch (torch.Tensor): Batch of normalized tensors. |
| 233 | mean (torch.Tensor or list): Mean used for normalization. |
| 234 | std (torch.Tensor or list): Standard deviation used for normalization. |
| 235 | |
| 236 | Returns: |
| 237 | torch.Tensor: batch of tensors without normalization applied to them. |
| 238 | """ |
| 239 | if isinstance(mean, list): |
| 240 | mean = torch.tensor(mean).to(device) |
| 241 | if isinstance(std, list): |
| 242 | std = torch.tensor(std).to(device) |
| 243 | |
| 244 | return batch * std.view(1, -1, 1, 1) + mean.view(1, -1, 1, 1) |
| 245 | |
| 246 | |
| 247 | ###################################################################### |