问题:
希望在pytorch中使用earlystopping,搜索后发现可以使用'pytorchtools'中的'EarlyStopping'。
教程中说使用 pip install pytorchtools 进行安装,这样安装的版本是0.0.2,
之后调用 from pytorchtools import EarlyStopping 即可,
但这样会报错 ImportError: cannot import name 'EarlyStopping' from 'pytorchtools'。
原因:
查看后发现用这种方式安装的'pytorchtools'是空的,里面没有'EarlyStopping'。
解决方法:
将如下代码(或地址中的代码)复制进去,或者直接在项目中新建一个pytorchtools.py文件,之后将代码复制进去后调用即可 ; )
import numpy as np
import torch
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):
"""
Args:
patience (int): How long to wait after last time validation loss improved.
上次验证集损失值改善后等待几个epoch
Default: 7
verbose (bool): If True, prints a message for each validation loss improvement.
如果是True,为每个验证集损失值改善打印一条信息
Default: False
delta (float): Minimum change in the monitored quantity to qualify as an improvement.
监测数量的最小变化,以符合改进的要求
Default: 0
"""
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
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):
'''
Saves model when validation loss decrease.
验证损失减少时保存模型。
'''
if self.verbose:
print(f'Validation loss decreased ({self.val_loss_min:.6f} --> {val_loss:.6f}). Saving model ...')
torch.save(model.state_dict(), 'checkpoint.pth') # 这里会存储迄今最优模型的参数
# torch.save(model, 'finish_model.pkl') # 这里会存储迄今最优的模型
self.val_loss_min = val_loss