How to calculate second derivative gradients for mixed precision. I try calling backward() twice but it gave the same gradients as first derivative.

```
self.scaler.scale(loss).backward()
self.scaler.scale(loss).backward()
```

How to calculate second derivative gradients for mixed precision. I try calling backward() twice but it gave the same gradients as first derivative.

```
self.scaler.scale(loss).backward()
self.scaler.scale(loss).backward()
```

Calling `backward`

multiple times will calculate the same gradients and accumulate them.

You would need to backward the derivatives again as described in this post.

1 Like