I am working on Biomedical Image Segmentation. For this regard, i need the implementation of SegNet model. I searched for SegNet implementation in many places but none of these provide me correct implementation. I got some implementations without using pre-trained encoder. But from the paper of SegNet, i knew that SegNet use pre-trained encoder which is trimmed portion of VGG-16 network trained on ImageNet dataset. I need the implementation in Keras.
N.B. There is a pretrained VGG-16 network available in keras. But that lacks Batch Normalization layers, which is present in the original paper in SegNet.
P.S. I cannot retrain the VGG-16 network on my own because of the scarcity of computational resource.
