Images feed to the ResNet 50

#1

The images feed into the ResNet 50 were not normalized(divided by 255) and they were also not normalized according to ResNet50

#2

Hey @raunaqsingh10, yes actually in Resnet50 after first convolution layer, there is a batchNormalization layer present, when we use this layer in our architecture, we do not need to normalize the inputs, as they are automatically normalized after first layer.

Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section. :blush:

#3

I’ve done as instructed by sir but I am not getting even close to the training and validation accuracy that sir got. Can you please look into the code and tell me where I am going wrong - https://drive.google.com/open?id=1K8iKcKgd-7AVyPhuICONBlhY2Gk05GtJ

#4

Hey @raunaqsingh10, try to increase number of epochs to 50.

#5

That did not help. But I cannot understand what is the problem, sir’s code worked perfectly fine

#6

Hey @raunaqsingh10, sorry for late reply is your dobt still there, or found the mistake, ?

#7

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.