search

bfortuner / pytorch_tiramisu

FC-DenseNet in PyTorch for Semantic Segmentation
MIT License
306 stars 66 forks source link

Training always starts with accuracy of 1.000 #22

Open gopinath-balu opened 5 years ago

gopinath-balu commented 5 years ago

Thank you so much @bfortuner for the implementation of this model in PyTorch. When I try to train the Network with the mentioned CamVid dataset, my training always starts with the Train Acc and Val Acc of 1.000. I have set the hyper-parameters as mentioned in the requirements section. Screenshot 2019-08-30 at 6 31 23 PM

In other words training error and validation error is always 0. Wondering if am missing something ??

KerryZack commented 1 year ago

maybe you can check the err function in the training.py.I replace the "return round(err,5)" with return err.item()