Table 11 Impact of fine-tuning vs. feature extraction on APV dataset performance.

From: A fine tuned EfficientNet-B0 convolutional neural network for accurate and efficient classification of apple leaf diseases

Training strategy

Test accuracy (%)

Test loss

Frozen Feature Extractor

(No Fine-tuning)

23.27

1.4722

Fine-Tuning Entire Model

(Proposed fine-tuned EfficientNet-B0)

99.69

0.0242

Back to article page