microsoft / Recursive-Cascaded-Networks

[ICCV 2019] Recursive Cascaded Networks for Unsupervised Medical Image Registration
https://arxiv.org/abs/1907.12353
MIT License
361 stars 87 forks source link

Training stops abruptly on colab #57

Open kirti-github opened 3 years ago

kirti-github commented 3 years ago

Hello, I tried running train.py on colab after changing the tensorflow imports to tensorflow compat so that the code could run on tensorflow2. During execution, it looks like the training stops abruptly and I didn't see any errors in the logs. I have used the command below to run the code and have attached the logs. !python train.py -n 3 -d datasets/brain.json train_logs.txt

I request you to suggest a workaround to resolve this. Thank you.