时间戳

首页 > 解决方案 > tensorflow：只能在 val_acc 可用的情况下保存最佳模型，跳过

python - tensorflow：只能在 val_acc 可用的情况下保存最佳模型，跳过

问题描述

我有一个问题tf.callbacks.ModelChekpoint。正如您在我的日志文件中看到的那样，警告总是出现在val_acc计算 的最后一次迭代之前。因此，Modelcheckpoint永远找不到val_acc

Epoch 1/30
1/8 [==>...........................] - ETA: 19s - loss: 1.4174 - accuracy: 0.3000
2/8 [======>.......................] - ETA: 8s - loss: 1.3363 - accuracy: 0.3500 
3/8 [==========>...................] - ETA: 4s - loss: 1.3994 - accuracy: 0.2667
4/8 [==============>...............] - ETA: 3s - loss: 1.3527 - accuracy: 0.3250
6/8 [=====================>........] - ETA: 1s - loss: 1.3042 - accuracy: 0.3333
WARNING:tensorflow:Can save best model only with val_acc available, skipping.
8/8 [==============================] - 4s 482ms/step - loss: 1.2846 - accuracy: 0.3375 - val_loss: 1.3512 - val_accuracy: 0.5000

Epoch 2/30
1/8 [==>...........................] - ETA: 0s - loss: 1.0098 - accuracy: 0.5000
3/8 [==========>...................] - ETA: 0s - loss: 0.8916 - accuracy: 0.5333
5/8 [=================>............] - ETA: 0s - loss: 0.9533 - accuracy: 0.5600
6/8 [=====================>........] - ETA: 0s - loss: 0.9523 - accuracy: 0.5667
7/8 [=========================>....] - ETA: 0s - loss: 0.9377 - accuracy: 0.5714
WARNING:tensorflow:Can save best model only with val_acc available, skipping.
8/8 [==============================] - 1s 98ms/step - loss: 0.9229 - accuracy: 0.5750 - val_loss: 1.2507 - val_accuracy: 0.5000

这是我训练 CNN 的代码。

callbacks = [
        TensorBoard(log_dir=r'C:\Users\reda\Desktop\logs\{}'.format(Name),
                    histogram_freq=1),
        ModelCheckpoint(filepath=r"C:\Users\reda\Desktop\checkpoints\{}".format(Name), monitor='val_acc',
                        verbose=2, save_best_only=True, mode='max')]
history = model.fit_generator(
        train_data_gen, 
        steps_per_epoch=total_train // batch_size,
        epochs=epochs,
        validation_data=val_data_gen,
        validation_steps=total_val // batch_size,
        callbacks=callbacks)

标签： pythontensorflowmachine-learningkerasdeep-learning

解决方案

我知道这些事情有时会令人沮丧。但是 tensorflow 要求您明确写出要计算的指标的名称

您实际上需要说“val_accuracy”

metric = 'val_accuracy'
ModelCheckpoint(filepath=r"C:\Users\reda.elhail\Desktop\checkpoints\{}".format(Name), monitor=metric,
                    verbose=2, save_best_only=True, mode='max')]

希望这会有所帮助=)

推荐阅读