pytorch tensorflow 的earlystopping方法

项目中使用到的早停法；

一、pytorch

import numpy as np
import torch
import os

class EarlyStopping:
    """Early stops the training if validation loss doesn't improve after a given patience."""
    def __init__(self, patience=7, verbose=False, delta=0, path='../weights', 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.val_loss_min = np.Inf
        self.delta = delta
        self.path = os.path.join(path,'best.pt')
        self.trace_func = trace_func
    def __call__(self, val_loss, model):

        score = -val_loss

        if self.best_score is None:
            self.best_score = score
            self.save_checkpoint(val_loss, model)
        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(val_loss, model)
            self.counter = 0

    def save_checkpoint(self, val_loss, model):
        '''Saves model when validation loss decrease.'''
        if self.verbose:
            self.trace_func(f'Validation loss decreased ({self.val_loss_min:.6f} --> {val_loss:.6f}).  Saving model ...')
        torch.save(model.state_dict(), self.path)
        self.val_loss_min = val_loss

二、tensorflow

import tensorflow as tf
import numpy as np
import args

class EarlyStopping:
    '''Early stop the training if validation loss doesn't improve after
    a given patience'''

    def __init__(self, patience=7, verbose=False,
                 delta=0, path='checkpoint.pt'):
        self.patience = patience
        self.verbose = verbose
        self.counter = 0
        self.best_score = None
        self.early_stop = False
        self.val_loss_min = np.Inf
        self.delta = delta
        self.path = path

    def __call__(self, val_loss, model):
        score = -val_loss

        if self.best_score is None:
            self.best_score = score
            self.save_checkpoint(val_loss, model)
        elif score < self.best_score + self.delta:
            self.counter += 1
            print(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(val_loss, model)
            self.counter = 0

    def save_checkpoint(self, val_loss, model):
        '''save model when validation loss decreas'''
        if self.verbose:
            print(f'validation loss decrease ({self.val_loss_min:.6f})')
        saver_to_save = tf.train.Saver()
        saver_to_save.save(model, args.save_dir + 'best')
        print('save success')
        self.val_loss_min = val_loss

三、train代码调用

early_stopping = EarlyStopping(patience=10, verbose=True)  # EarlyStopping 初始化

early_stopping(val_loss_total.average, sess)
# 若满足 early stopping 要求
if early_stopping.early_stop:
    print("Early stopping")
    # 结束模型训练
    break