How is the threshold set for the FBeta, Precision and Recall classes?

[4722794]

Hey @nojeffrey, I managed to handle the imbalance using FocalLoss() as a loss function. The new model significantly improved the precision, recall and f1 score on a comparable test set.
This might help:

Applying FocalLoss in fastai

I’m trying to apply FocalLoss in fastai as a custom loss function to train a model that has dense multi-label classification problem. I found this code for pytorch to calc FocalLoss: https://github.com/clcarwin/focal_loss_pytorch import torch import torch.nn as nn import torch.nn.functional as F from torch.autograd import Variable class FocalLoss(nn.Module): def __init__(self, gamma=0, alpha=None, size_average=True): super(FocalLoss, self).__init__() self.gamma = gamma …