Improving the accuracy of a model, especially one based on convolutional neural networks (CNNs) like in your case, can be approached from several angles like data augmentation, it artificially increases the size and variability of your training dataset by applying a series of transformations (e.g., rotations, translations, flipping, scaling, etc.), you can use ‘imageDataAugmenter’ as it configures a set of preprocessing options for image augmentation, such as resizing, rotation, and reflection. This can help the model generalize better. Also, consider adding or removing layers accordingly, hyperparameter tuning and transfer learning.
For more information, you can refer to the documentation links below –
