Early Stopping在Pytorch中的应用

在深度学习中Early Stopping可以有效地防止过拟合。但是在Pytorch中似乎还没有官方实现Early Stopping的类。Bjarten/early-stopping-pytorch这个Github仓库（点击进入）实现了一个Early Stopping类，针对的指标是validation loss。参考其代码修改为可以任意指定monitor指标，并根据自己指定的monitor指标确定Early Stopping的方向（找monitor的最大值或最小值）。

class EarlyStopping:
    """Early stops the training if validation loss doesn't improve after a given patience."""
	
    def __init__(self, patience=15, verbose=False, delta=0, path='checkpoint.pt', trace_func=print):
        """
        Args:
            patience (int): How long to wait after last time validation loss improved.
                            Default: 7
            verbose (bool): If True, prints a message for each validation loss improvement. 
                            Default: False
            delta (float): Minimum change in the monitored quantity to qualify as an improvement.
                            Default: 0
            path (str): Path for the checkpoint to be saved to.
                            Default: 'checkpoint.pt'
            trace_func (function): trace print function.
                            Default: print            
        """
        self.patience = patience
        self.verbose = verbose
        self.counter = 0
        self.best_score = None
        self.early_stop = False
        self.monitor_extreme = 0
        self.delta = delta
        self.path = path
        self.trace_func = trace_func

    def __call__(self, monitor, mode, state):
        if mode == 'min':
            score = -monitor
        elif mode == 'max':
            score = monitor

        if self.best_score is None:
            self.best_score = score
            self.save_checkpoint(monitor, state)
        elif score < self.best_score + self.delta:
            self.counter += 1
            self.trace_func(f'EarlyStopping counter: {self.counter} out of {self.patience}')
            if self.counter >= self.patience:
                self.early_stop = True
        else:
            self.best_score = score
            self.save_checkpoint(monitor, state)
            self.counter = 0

    def save_checkpoint(self, monitor, state):
        '''Saves model when monitor gets better value.'''
        if self.verbose:
            self.trace_func(f'Monitor gets better value: ({self.monitor_extreme:.6f} --> {monitor:.6f}).  Saving model ...')
        torch.save(state, self.path)
        print('\n------------ Save best model ------------\n')
        self.monitor_extreme = monitor