Media-Smart / vedadet

A single stage object detection toolbox based on PyTorch
Apache License 2.0
498 stars 128 forks source link

How to print training/validation loss? #72

Open pasquale90 opened 2 years ago

pasquale90 commented 2 years ago

During training, a single line for each epoch is printed, nevertheless the loss is not printed. Neither during validation. For the validation I managed to print the metrics (ap,recall,mAP) for each single epoch, using iteratively the validation code provided and then parsing the lines of my custom script's output file, but since I am trying to train on my custom dataset, I would like to obtain a clearer insight of both the training and validation process by printing the losses (either focal ,iou, L1, crossentropy or even the global loss) .. What is the simplest way on retrieving them? Thanks!