ai-med / quickNAT_pytorch

PyTorch Implementation of QuickNAT and Bayesian QuickNAT, a fast brain MRI segmentation framework with segmentation Quality control using structure-wise uncertainty
MIT License
101 stars 36 forks source link

'phase' not used in cm_per_epoch() #24

Closed iagooteroc closed 4 years ago

iagooteroc commented 4 years ago

The "phase" parameter in the cm_per_epoch() function is not passed to the dice_confusion_matrix() function. Instead, the "train" mode is used even in the validation phase.

https://github.com/ai-med/quickNAT_pytorch/blob/920d85ea5cfb621a5f574796677778df58e31d55/utils/log_utils.py#L62

abhi4ssj commented 4 years ago

Good catch! I updated the line. Thanks.