0

所以我试图在 colab 上训练一个模型，这将需要我大约 70-72 小时的持续运行时间。我有一个免费帐户，所以我经常因为过度使用或不活动而被踢，这意味着我不能将历史记录转储到 pickle 文件中。

history = model.fit_generator(custom_generator(train_csv_list,batch_size), steps_per_epoch=len(train_csv_list[:13400])//(batch_size), epochs=1000, verbose=1,  callbacks=[stop_training], validation_data=(x_valid,y_valid))

我在回调方法中找到了 CSVLogger 并将其添加到我的回调中，如下所示。但由于某种原因，它不会创建 model_history_log.csv。我没有收到任何错误或警告。我做错了什么？我的目标是在整个训练过程中只保存准确性和损失

class stop_(Callback): 
    def on_epoch_end(self, epoch, logs={}):
        model.save(Path("/content/drive/MyDrive/.../model" +str(int(epoch))))
        CSVLogger("/content/drive/MyDrive/.../model_history_log.csv", append=True)
        if(logs.get('accuracy') > ACCURACY_THRESHOLD):
                print("\nReached %2.2f%% accuracy, so stopping training!!" %(ACCURACY_THRESHOLD*100))   
                self.model.stop_training = True
stop_training = stop_()

另外，由于我在每个时期都保存了模型，模型是否保存了这些信息？到目前为止我还没有发现任何东西，我怀疑它是否可以节省准确性、损失、val 准确性等

4

1 回答 1

0

认为你想写你的回调如下

class STOP(tf.keras.callbacks.Callback):
    def __init__ (self, model, csv_path, model_save_dir, epochs, acc_thld): # initialization of the callback
        # model is your compiled model
        # csv_path is path where csv file will be stored
        # model_save_dir is path to directory where model files will be saved
        # number of epochs you set in model.fit
        self.model=model
        self.csv_path=csv_path
        self.model_save_dir=model_save_dir
        self.epochs=epochs
        self.acc_thld=acc_thld
        self.acc_list=[] # create empty list to store accuracy
        self.loss_list=[] # create empty list to store loss
        self.epoch_list=[] # create empty list to store the epoch
        
    def on_epoch_end(self, epoch, logs=None):  # method runs on the end of each epoch  
        savestr='_' + str(epoch+1) + '.h5' # model will be save as an .h5 file with name _epoch.h5
        save_path=os.path.join(self.model_save_dir, savestr)
        acc= logs.get('accuracy') #get the accuracy for this epoch
        loss=logs.get('loss') # get the loss for this epoch       
        self.model.save (save_path)   # save the model     
        self.acc_list.append(logs.get('accuracy'))          
        self.loss_list.append(logs.get('loss'))
        self.epoch_list.append(epoch + 1)        
        if acc > self.acc_thld or epoch+1 ==epochs: # see of acc >thld or if this was the last epoch
            self.model.stop_training = True # stop training
            Eseries=pd.Series(self.epoch_list, name='Epoch')
            Accseries =pd.Series(self.acc_list, name='accuracy')
            Lseries=pd.Series(self.loss_list, name='loss')
            df=pd.concat([Eseries, Lseries, Accseries], axis=1) # create a dataframe with columns epoch loss accuracy
            df.to_csv(self.csv_path, index=False) # convert dataframe to a csv file and save it
            if acc  > self.acc_thld:
                print ('\nTraining halted on epoch ', epoch + 1, ' when accuracy exceeded the threshhold')

然后在你运行 model.fit 之前使用代码

epochs=20 # set number of epoch for model.fit and the callback
sdir=r'C:\Temp\stooges' # set directory where save model files and the csv file will be stored
acc_thld=.98 # set accuracy threshold
csv_path=os.path.join(sdir, 'traindata.csv') # name your csv file to be saved in sdir
callbacks=STOP(model, csv_path, sdir, epochs, acc_thld) # instantiate the callback

请记住在 model.fit 中设置回调 = 回调。我在一个简单的数据集上对此进行了测试。在精度超过 0.98 的阈值之前，它只运行了 3 个 epoch。因此，由于它运行了 3 个 epoch，它在 sdir 中创建了 3 个保存模型文件，标记为

_1.h5
_2.h5
_3.h5

它还创建了标记为 traindata.csv 的 csv 文件。csv 文件内容为

Epoch    loss        accuracy
   1     8.086007    .817778
   2     6.911876    .974444
   3     6.129871    .987778
于 2022-02-24T08:04:20.427 回答