Timeline for Explanation behind the calculation of training loss in deep learning model
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 23, 2019 at 2:37 | comment | added | Beginner | you are really superb | |
| Sep 23, 2019 at 2:18 | comment | added | 1tan Wang | When calculating averages, we need its total amount. Multiply avg_loss with 4 to get the total amount of loss in the first 4 batches because avg_loss of the first 4 batches is calculated from total amount divided by 4. | |
| Sep 23, 2019 at 2:16 | vote | accept | Beginner | ||
| Sep 23, 2019 at 2:15 | comment | added | Beginner | Another noob question, why we multiplied avg_loss with 4?Edit:Oh.. I got it...thanks. | |
| Sep 23, 2019 at 2:12 | comment | added | 1tan Wang | No worries. I've updated with the equations. | |
| Sep 23, 2019 at 2:09 | history | edited | 1tan Wang | CC BY-SA 4.0 |
added 395 characters in body
|
| Sep 23, 2019 at 2:07 | comment | added | Beginner |
Thanks Wang. Could you please explain me in form of some equation or by giving an instance or if you could point to some resources. I am finding it hard to build an intuition of it as I also find the following train_loss in many cases-train_loss += loss.item()*data.size(0)
|
|
| Sep 23, 2019 at 2:01 | history | answered | 1tan Wang | CC BY-SA 4.0 |