|
Figure 5. Training loss and validation loss curves before and after the introduction of transfer learn-
ing in ResNet50. (aBog'liq Classification Method of Significant Rice Pests Ba Физика-курси-1-қисм.-Кодиров-О, ТДИУ, HSyflfAupzrtVxmeX2kSjtbqHjgjAGFqyWgWY1gY, Введение в физику ускорителей заряженных частиц by Иссинский И Б, O\'lchash usullari va vositalari. MamajonovA.A. Sattorov M.O., mustaqil ish 12212121212, Futbol maydonlari va o`lchamlari, TEST argos — копия, «ТЕХНОЛОГИК ЖАРАЁНЛАРНИ АВТОМАТЛАШТИРИШ ВА МОДЕЛЛАШТИРИШ», sinfdan-tashqari-tarbiyaviy-ishlarni-tashkil-qilishning-ilmiy-va-nazariy-asoslariFigure 5. Training loss and validation loss curves before and after the introduction of transfer learn-
ing in ResNet50. (a) ResNet50 trained from scratch; (b) ResNet50 with Transfer learning introduced.
(a)
(b)
Figure 6. Training loss and validation loss curves before and after the introduction of transfer learn-
ing in VGG16. (a) VGG16 trained from scratch; (b) VGG16 with Transfer learning introduced.
(a)
(b)
Figure 7. Training loss and validation loss curves before and after the introduction of transfer learn-
ing in MobileNet. (a) MobileNet trained from scratch; (b) MobileNet with Transfer learning intro-
duced.
Figure 8 displays the accuracy curves of the validation sets of ResNet, VGGNet and
MobileNet networks before and after using the transfer learning strategy in turn. It shows
that the initial validation accuracy of the ResNet50, VGG16, and MobileNet classification
network models increases after the introduction of transfer learning, and the training pro-
cess curves using transfer learning converge better and more smoothly. It is worth men-
tioning that the validation accuracy of the network models after the introduction of
Figure 5.
Training loss and validation loss curves before and after the introduction of transfer learning
in ResNet50. (a) ResNet50 trained from scratch; (b) ResNet50 with Transfer learning introduced.
Agronomy 2022, 12, x FOR PEER REVIEW
9 of 20
(a)
(b)
Figure 5. Training loss and validation loss curves before and after the introduction of transfer learn-
ing in ResNet50. (a) ResNet50 trained from scratch; (b) ResNet50 with Transfer learning introduced.
(a)
(b)
Figure 6. Training loss and validation loss curves before and after the introduction of transfer learn-
ing in VGG16. (a) VGG16 trained from scratch; (b) VGG16 with Transfer learning introduced.
(a)
(b)
|
|
Bosh sahifa
Aloqalar
Bosh sahifa
Figure 5. Training loss and validation loss curves before and after the introduction of transfer learn-
ing in ResNet50. (a
|