luna
luna
Hello @JordanMakesMaps, I checked the preprocessing for resnets and it doesn't do anything, so if someone wants to use pretrained imagenet weights he shouldn't scale his images to the range...
I checked the paper "Deep Residual Learning for Image Recognition" I think the images were normalised, they were substracted by the mean. 
Thank you @JordanMakesMaps for your answer, I don't know why I was confused, you made it clear for me, thank you.
hello @dennywangtenk did adding dropout help you overcome the problem of overfitting ?
Hello, Yes there isn't dropout layers in the implementation of unet, but you can use regularizers set_regularization(model, kernel_regularizer=keras.regularizers.l2(0.001),bias_regularizer=keras.regularizers.l2(0.001)) you can also try data augmentation. But if it is necessary to...
Hi, I'm facing the same problem, please tell me if you resolved it ?
got the same error when I runned docker-compose up