You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi! I have a few questions regarding implementation details. Here is the article.
Does we need to manually implement backward pass? As I can see in torch it is manually implemented.
In the original article authors use rescaling mode (additional math operation) due to better numerical stability of results (because probabilities in normal mode become zeros so fast). Should it be used here? Or burn handles numerical stability automatically under the hood?
Is there some standard way to measure performance inside burn? Or should I use criterion and manually implement benchmarks?
implement ctc loss function. Can complete: #1049
The text was updated successfully, but these errors were encountered: