- Add loss_custom.py to the folder (same directory with loss.py) and edit train.py
- Change import from loss to loss_custom in main.py
from utils.loss import ComputeLoss
from utils.loss_custom import ComputeLoss
- play with hyperparameter "n", "gamma", "sigma" with parser
n: softscore1 assignment
gamma : softscore1 assignment
sigma : softscore2 assignment
- Detail implementation of our method is in loss_custom.py > Compute_Loss > build_targets_custom1
- build_targets_custom: implemented with for loops => very long computation time
- build_targets_custom1: modified computation into tensor => much faster but still slower than the original wich has less targets (Binary)
Results: https://wandb.ai/wonseokjeong/YOLOv5?workspace=user-wonseokjeong
Results: https://wandb.ai/wonseokjeong/train?workspace=user-wonseokjeong
Results: https://wandb.ai/wonseokjeong/YOLO_VOC?workspace=user-wonseokjeong
Helps training in the early stage but interrupts the the model understanding and downgrades the MAP results.