keras ModelCheckpoint & tensorboard

 

1. more scientific model training and model save

filepath = 'model-ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5'
checkpoint = ModelCheckpoint(filepath, monitor='val_loss', verbose=1, save_best_only=True, mode='min')
# fit model
model.fit(x, y, epochs=20, verbose=2, callbacks=[checkpoint], validation_data=(x, y))

After save_best_only opens, as follows:

 ETA: 3s - loss: 0.5820Epoch 00017: val_loss did not improve

If val_loss will improve the preservation, no increase will not be saved.

ModelCheckpoint

keras.callbacks.ModelCheckpoint(filepath, monitor='val_loss', verbose=0, save_best_only=False, save_weights_only=False, mode='auto', period=1)

The callback function to save the model after each epochfilepath

filepathIt may be formatted string, which will be a placeholder epochvalue and passed on_epoch_endthe logskeywords filled

For example, filepathif it is weights.{epoch:02d-{val_loss:.2f}}.hdf5, it will correspond to a plurality of files and validation sets epoch generation loss.

parameter

• filename: string that holds the model of Path

• monitor: the value to be monitored

• verbose: information presentation mode, 0 or 1

• save_best_only: When set True, it will save only the best performance on the verification set model

• mode: 'auto', 'min ', one of 'max', in save_best_only=Truedetermining the best model performance evaluation criterion, e.g., when the monitored value val_acc, the mode should be max, when the detection value val_loss, the pattern should be min. In automode, the evaluation criteria are monitored automatically by inference value name.

• save_weights_only: If set to True, only save the model weights, or save the entire model (including the model structure, configuration information, etc.)

• period: Number epoch interval between CheckPoint.

 

2. How to use tensorboard in the keras

RUN = RUN + 1 if 'RUN' in locals() else 1   # locals() 函数会以字典类型返回当前位置的全部局部变量。

    LOG_DIR = model_save_path + '/training_logs/run{}'.format(RUN)
    LOG_FILE_PATH = LOG_DIR + '/checkpoint-{epoch:02d}-{val_loss:.4f}.hdf5'   # 模型Log文件以及.h5模型文件存放地址

    tensorboard = TensorBoard(log_dir=LOG_DIR, write_images=True)
    checkpoint = ModelCheckpoint(filepath=LOG_FILE_PATH, monitor='val_loss', verbose=1, save_best_only=True)
    early_stopping = EarlyStopping(monitor='val_loss', patience=5, verbose=1)

    history = model.fit_generator(generator=gen.generate(True), steps_per_epoch=int(gen.train_batches / 4),
                                  validation_data=gen.generate(False), validation_steps=int(gen.val_batches / 4),
                                  epochs=EPOCHS, verbose=1, callbacks=[tensorboard, checkpoint, early_stopping])

 

All play a role in the callback function:

• EarlyStopping patience: When Early 
  (. 1) STOP is activated (e.g., loss found on a training epoch is not decreased compared), then after a patience stop training epoch. 
  (2) mode: 'auto' , 'min', one of 'max', in min mode, if the detection value stops decreasing aborting training. In max mode, when the detected value is no longer increased training is stopped.

• Model checkpoint ModelCheckpoint 
  (. 1) save_best_only: When set to True, the verification will only save the best performance on the current model 
  (2) mode: 'auto' , 'min', 'max' one, in save_best_only = True determining the best model performance evaluation criterion, e.g., when monitoring is val_acc, mode should be max, when the detection value val_loss, mode should be min. In auto mode, inferring evaluation criteria to be monitored automatically by the value of the name. 
  (3) save_weights_only: If set to True, only save the model weights, or to save the entire model (including the model structure, configuration information, etc.) 
  (. 4) period: Number epoch interval between CheckPoint

• Visualization tensorboard write_images: whether the model weights in the form of visual images