如何在Keras的每个时代保存培训历史记录?

时间:2018-05-02 05:14:10

标签: python tensorflow keras

我无法让我的电脑一整天都在运行,为此我需要在每个时代之后保存培训历史记录。例如,我在一天内训练了100个时代的模型,第二天,我想再训练50个时代。我需要为整个150个时期生成损失与时代和精确度与时代图的关系。我正在使用fit_generator方法。有没有办法在每个纪元后保存训练历史记录(最有可能使用Callback)?我知道如何在培训结束后保存培训历史。我正在使用Tensorflow后端。

4 个答案:

答案 0 :(得分:2)

我有类似的要求,我采取了一种天真的方法。

1.Python代码运行50个时代:
我保存了模型的历史和模型本身训练了50个时代。 history = model.fit_generator(......) # training the model for 50 epochs model.save("trainedmodel_50Epoch.h5") # saving the model with open('trainHistoryOld', 'wb') as handle: # saving the history of the model dump(history.history, handle) 用于存储受过训练的模型的完整历史记录。

from keras.models import load_model
model = load_model('trainedmodel_50Epoch.h5')# loading model trained for 50 Epochs

hstry = model.fit_generator(......) # training the model for another 50 Epochs

model.save("trainedmodel_50Epoch.h5") # saving the model 

with open('trainHistoryOld', 'wb') as handle: # saving the history of the model trained for another 50 Epochs
    dump(hstry.history, handle)

from pickle import load
import matplotlib.pyplot as plt

with open('trainHistoryOld', 'rb') as handle: # loading old history 
    oldhstry = load(handle)

oldhstry['loss'].extend(hstry['loss'])
oldhstry['acc'].extend(hstry['acc'])
oldhstry['val_loss'].extend(hstry['val_loss'])
oldhstry['val_acc'].extend(hstry['val_acc'])

# Plotting the Accuracy vs Epoch Graph
plt.plot(oldhstry['acc'])
plt.plot(oldhstry['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()

# Plotting the Loss vs Epoch Graphs
plt.plot(oldhstry['loss'])
plt.plot(oldhstry['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()

2.Python代码,用于加载经过训练的模型和另外50个时期的训练:

UITableView

您也可以像前面提供的答案中提到的那样创建自定义类。

答案 1 :(得分:2)

Keras具有CSVLogger回调,该回调似乎完全可以满足您的需要:Callbacks - Keras Documentation

从文档中:

  

“将历元结果传输到csv文件的回调。”

它具有用于添加到文件的附加参数。再次,从文档中:

  

“追加:True:如果文件存在则追加(用于继续训练)。False:覆盖现有文件”

from keras.callbacks import CSVLogger

csv_logger = CSVLogger("model_history_log.csv", append=True)
model.fit_generator(...,callbacks=[csv_logger])

答案 2 :(得分:1)

要保存模型历史记录,您有两种选择。

  1. 使用keras ModelCheckPoint回调类
  2. 创建自定义类
  3. 以下是如何创建自定义检查点回调类。

    class CustomModelCheckPoint(keras.callbacks.Callback):
        def __init__(self,**kargs):
            super(CustomModelCheckPoint,self).__init__(**kargs)
            self.epoch_accuracy = {} # loss at given epoch
            self.epoch_loss = {} # accuracy at given epoch
            def on_epoch_begin(self,epoch, logs={}):
                # Things done on beginning of epoch. 
                return
    
            def on_epoch_end(self, epoch, logs={}):
                # things done on end of the epoch
                self.epoch_accuracy[epoch] = logs.get("acc")
                self.epoch_loss[epoch] = logs.get("loss")
                self.model.save_weights("name-of-model-%d.h5" %epoch) # save the model
    

    现在使用回拨类

    checkpoint = CustomModelCheckPoint()
    model.fit_generator(...,callbacks=[checkpoint])
    

    现在checkpoint.epoch_accuracy字典包含给定时期的准确度,checkpoint.epoch_loss字典包含给定时期的损失

答案 3 :(得分:0)

您可以按如下方式保存培训历史记录

function delRows51() {
  var ss = SpreadsheetApp.getActiveSheet();
  ss.deleteRows(51, ss.getMaxRows() - 50);
};

要保存每次训练后的训练历史记录

hist = model.fit_generator(generator(features, labels, batch_size), samples_epoch=50, nb_epoch=10)
import pickle
with open('text3', 'wb') as f:
    pickle.dump(hist.history, f)

对于检查点

import pickle
hist1 = []
for _ in range(10):
   hist = model.fit(X_train, y_train, epochs=1, batch_size=batch_size, validation_split=0.1)
   hist1.append(hist.history)

with open('text3', 'wb') as f:
    pickle.dump(hist1.history, f)