I am training a VGG16 net using transfer learning. I have removed the fully connected layers and used fine tuning to classify objects into few categories but I have faced below problems:
1.I have high dimensional images ( e.g. 2400 * 2800 3).. converting to 224 224* 3 , there is huge loss of information. How can we use high dimensional images without loss in VGG16?
2.Can we use any size of images to train the model . if yes then how