Training of deeplab-mobilenet and deeplab-xception failed
LimJiaJing opened this issue · 2 comments
I tried reproducing the results mentioned in the paper. To train deeplab-xception and deeplab-mobilenet, I simply changed "./train.py -c config.1_FRLR.unetxst.yml" to "./train.py -c config.1_FRLR.deeplab-xception.yml" and "./train.py -c config.1_FRLR.deeplab-mobilenet.yml". The training successfully starts but no improvement in performance occurs. I did not change any of the configurations and the training stops at epoch 21 for both models. Thanks for your time and I look forward to your guidance.
Have you worked with the most recent version of the repository?
Last week I merged this PR, downgrading from TensorFlow 2.7 to 2.5.
Re-creating your Python environment with the most recent requirements.txt should resolve your issue. Please let us know if it does.
Yes, it has solved the problem. Thank you!