Size of input training images

0bserver07 / One-Hundred-Layers-Tiramisu

Keras Implementation of The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation by (Simon Jégou, Michal Drozdzal, David Vazquez, Adriana Romero, Yoshua Bengio)

https://arxiv.org/abs/1611.09326

MIT License

197 stars 54 forks source link

Size of input training images #20

Open khiemkhanh98 opened 6 years ago

khiemkhanh98 commented 6 years ago

I want to train Tiramisu on my own custom dataset. Can I do it with different size images or I can only use images with size like the Camvid dataset?