Evaluating performance of pre-trained models for diabetic retinopathy detection with a minimal dataset using transfer learning

HIGHLIGHTS

• What: This study explores the performance of six pre-trained CNN models-DenseNet201, ResNet152, VGG16, InceptionV3, MobileNet, and EfficientNetB0-in detecting DR with a minimal dataset, adjusting the number of epochs from 5 to 15. Highlighting strategies https://www.indjst.org/ such as color and geometric transformations, random erasing, and GANs, the review demonstrates their efficacy in boosting model performance across diverse domains, including computer vision, natural language processing, security, and healthcare. The authors assessed the trained models on the test dataset using the evaluate_generator function , which calculates evaluation metrics like accuracy based on the model`s . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.