Additional Classes Effect on Model Accuracy using Transfer Learning
This empirical research study discusses how much the model’s accuracy changes when adding a new image class by using a pre-trained model with the same labels and measuring the precision of the previous classes to observe the changes. The purpose is to determine if using transfer learning is benefici...
| Main Author: | |
|---|---|
| Format: | Others |
| Language: | English |
| Published: |
Högskolan i Gävle, Datavetenskap
2020
|
| Subjects: | |
| Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-33970 |