Sharif Amit Kamran, PhD

icon indicating a website link www.sharifamit.com

icon company Johnson & Johnson icon location Reno, Nevada icon location Working on Deep learning for Bio-medical Imaging and Computer Vision. Designing robust generative architectures trained with limited data.

Results 5 comments of Sharif Amit Kamran, PhD

whether we need to pay attention to some details during training?

Hi, could you elaborate the problem you are facing? As far as the training goes, we don't change any hyperparameters during training.

whether we need to pay attention to some details during training?

Hi, you are on the right track. After training, loop over all the models and then print the metics for each to find the best snapshot. As GAN doesn't converge...

whether we need to pay attention to some details during training?

I have trained the model for 100 epochs. After training, I loaded the weights of the best performing Coarse and Fine Generator ( For the same epoch) and then trained...

whether we need to pay attention to some details during training?

ChaseDB doesnt come with training and test splits. Which images are you using for Chase-DB for testing ? Maybe the evaluation technique + test images you are using is giving...

whether we need to pay attention to some details during training?

F1-scrore is calculated using Precision and Sensitivity. We used pycm library. ``` import pycm cm = ConfusionMatrix(actual_vector=y_true, predict_vector=y_pred) print("Specificity: " + str(cm.TNR[1])) print("Sensitivity: " + str(cm.TPR[1])) print("Accuracy : " +...