Fully Convolutional Network Training Image Size

Question

I\'m trying to replicate the results of Fully Convolutional Network (FCN) for Semantic Segmentation using TensorFlow.

I\'m stuck on feeding training images into the

Answer 1

1. You can use batch size = 1
2. You can resize images to fixed size like 256,256
3. You can resize each batch to median image size of it's content.