Here (XNet-TF.Keras) is the XNet updated with tf 2.x. However, I'm using it just for casual stuff and so I only use keras official EfficientNet as an encoder. But other models can be integrated.
@MrGiovanni thanks for such concise implementation of unet++ in keras. One request, could you please consider adding XNet and NestNet to the qubvel/segmentation_models. The keras implementation of these two is missing there and not has been included yet. I think If it's included it surely will reach many practitioners to use xnet and nestnet models arch. Also, qubel repo is updated with tf 2.x. But the good thing is there is nothing big code changing is needed on your side and others. Please let me know if there's any known issue regarding this.
Here (XNet-TF.Keras) is the XNet updated with
tf 2.x. However, I'm using it just for casual stuff and so I only usekerasofficial EfficientNet as an encoder. But other models can be integrated.@MrGiovanni thanks for such concise implementation of unet++ in
keras. One request, could you please consider addingXNetandNestNetto the qubvel/segmentation_models. Thekerasimplementation of these two is missing there and not has been included yet. I think If it's included it surely will reach many practitioners to use xnet and nestnet models arch. Also, qubel repo is updated withtf 2.x. But the good thing is there is nothing big code changing is needed on your side and others. Please let me know if there's any known issue regarding this.