QJ-Chen

Puzzles about Inconsistency between code and article

4

```python # losses.sliced_sm def sliced_score_estimation(score_net, samples, n_particles=1): dup_samples = samples.unsqueeze(0).expand(n_particles, *samples.shape).contiguous().view(-1, *samples.shape[1:]) dup_samples.requires_grad_(True) vectors = torch.randn_like(dup_samples) vectors = vectors / torch.norm(vectors, dim=-1, keepdim=True) grad1 = score_net(dup_samples) # H, estimation of...

In model.attention AttentionModule1.shortcut_short is not used. You calculate the shortcut with the downsample weights. ```python shortcut_short = self.soft_resdown3(x_s) ``` AttentionModule3.shortcut_short is unnecessary.