search

IAmSuyogJadhav / 3d-mri-brain-tumor-segmentation-using-autoencoder-regularization

Keras implementation of the paper "3D MRI brain tumor segmentation using autoencoder regularization" by Myronenko A. (https://arxiv.org/abs/1810.11654).
MIT License
369 stars 113 forks source link

tf.keras compatibility #42

Open olyaee opened 4 years ago

olyaee commented 4 years ago

Hi, I am trying to run the code using tf2 Keras. However, I receive the following error which is related to the loss_VAE function:

_SymbolicException: Inputs to eager execution function cannot be Keras symbolic tensors, but found [<tf.Tensor 'Dec_VAE_VDraw_Var/Identity:0' shape=(None, 128) dtype=float32>, <tf.Tensor 'Dec_VAE_VDraw_Mean/Identity:0' shape=(None, 128) dtype=float32>]`

I know its not a bug, but I will appreciate any suggestion to solve it.

Please find the complete NOTEBOOK here.

IAmSuyogJadhav commented 4 years ago

This script is old and was not designed for Tensorflow 2.0. You will need an older version.