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
Hello author, I tested the Visa dataset using a model that has been trained in engineering and the results were good. However, when I used the Visa dataset, created a meta.json file, and trained for 15 epochs, the testing results were very poor. What is the reason for this?
The text was updated successfully, but these errors were encountered:
Similarly, when I train the replicated model myself and test it on the VISA dataset, the results are not as good as those of the author, with a difference of about 1 to 2 percentage points
Hello author, I tested the Visa dataset using a model that has been trained in engineering and the results were good. However, when I used the Visa dataset, created a meta.json file, and trained for 15 epochs, the testing results were very poor. What is the reason for this?
The text was updated successfully, but these errors were encountered: