keras u_网模型分割精度差

我正在尝试我的第一个分割模型，用u_网分割脑部MRI病变，问题是我得到的结果精度很差。我的内置网络和代码。 我试图改变损失函数，但同样的问题

def Tversky(targets, inputs, alpha=ALPHA, beta=BETA, smooth=1e-6):
        inputs = K.flatten(inputs)
        targets = K.flatten(targets)
        TP = K.sum((inputs * targets))
        FP = K.sum(((1-targets) * inputs))
        FN = K.sum((targets * (1-inputs)))
        Tversky = (TP + smooth) / (TP + alpha*FP + beta*FN + smooth) 
        return Tversky
    
def dice_coefficient(y_true, y_pred, smooth=1.,eps: float = 1e-9):
    y_true_f = K.flatten(y_true)
    y_pred_f = K.flatten(y_pred)
    intersec = K.sum(y_true_f * y_pred_f)
    union = K.sum(y_pred_f) + K.sum(y_true_f)+eps           
    return (2*intersec + eps) / union