focal loss 的 二分类以及多分类实现

1、tf 版本

# 二分类
def binary_focal_loss(gamma=2, alpha=0.25):
    alpha = tf.constant(alpha, dtype=tf.float32)
    gamma = tf.constant(gamma, dtype=tf.float32)
    def focal_loss_sigmoid(y_true, y_pred):
        labels = tf.cast(y_true, tf.float32)
        L=-labels*(1-alpha)*((1-y_pred)**gamma)*K.log(y_pred)-\
          (1-labels)*alpha*(y_pred**gamma)*K.log(1-y_pred)
        return L    
    return focal_loss_sigmoid

2、torch 版本

class FocalLoss(nn.Module):
    def __init__(self, gamma = 2, alpha = 1, size_average = True):
        super(FocalLoss, self).__init__()
        self.gamma = gamma
        self.alpha = alpha
        self.size_average = size_average
        self.elipson = 0.000001
    
    def forward(self, logits, labels):
        """
        cal culates loss
        logits: batch_size * labels_length * seq_length
        labels: batch_size * seq_length
        """
        if labels.dim() > 2:
            labels = labels.contiguous().view(labels.size(0), labels.size(1), -1)
            labels = labels.transpose(1, 2)
            labels = labels.contiguous().view(-1, labels.size(2)).squeeze()
        if logits.dim() > 3:
            logits = logits.contiguous().view(logits.size(0), logits.size(1), logits.size(2), -1)
            logits = logits.transpose(2, 3)
            logits = logits.contiguous().view(-1, logits.size(1), logits.size(3)).squeeze()
        assert(logits.size(0) == labels.size(0))
        assert(logits.size(2) == labels.size(1))
        batch_size = logits.size(0)
        labels_length = logits.size(1)
        seq_length = logits.size(2)

        # transpose labels into labels onehot
        new_label = labels.unsqueeze(1)
        label_onehot = torch.zeros([batch_size, labels_length, seq_length]).scatter_(1, new_label, 1)

        # calculate log
        log_p = F.log_softmax(logits)
        pt = label_onehot * log_p
        sub_pt = 1 - pt
        fl = -self.alpha * (sub_pt)**self.gamma * log_p
        if self.size_average:
            return fl.mean()
        else:
            return fl.sum()