Validation Accuracy doesn't increase.
2 visualizzazioni (ultimi 30 giorni)
Mostra commenti meno recenti
Hello, I wonder if any of you who have used deep learning on matlab can help me to troubleshoot my problem. I don't understand why my model's validation accuracy doesn't increase. I used pre-trained AlexNet and My dataset just worked well in Python(PyTorch). I guess there is something problem with dataloader or image type(double, uint8, ...etc).
please help me. Thank you.
![tranfer1.JPG](https://www.mathworks.com/matlabcentral/answers/uploaded_files/206163/tranfer1.jpeg)
And here is my code.
![1.JPG](https://www.mathworks.com/matlabcentral/answers/uploaded_files/206164/1.jpeg)
![2.JPG](https://www.mathworks.com/matlabcentral/answers/uploaded_files/206165/2.jpeg)
![3.JPG](https://www.mathworks.com/matlabcentral/answers/uploaded_files/206166/3.jpeg)
![캡처.JPG](https://www.mathworks.com/matlabcentral/answers/uploaded_files/206167/%EC%BA%A1%EC%B2%98.jpeg)
1 Commento
Sahar Salimpour
il 7 Feb 2021
Hello, i have the same problem. The validation accuracy is a fixed value and doesn't change at all(0.3), did you find any solution ?
Risposte (1)
Jack Xiao
il 21 Feb 2021
reduce the initial learning rate to a smaller value such as 0.0001
0 Commenti
Vedere anche
Categorie
Scopri di più su Image Data Workflows in Help Center e File Exchange
Prodotti
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!