从 Tensorflow Keras 检查点重新加载最佳权重 [英] Reload best weights from Tensorflow Keras Checkpoints

问题描述

有没有办法在训练结束后重新加载某个时期的权重或 ModelCheckpoint 创建的模型检查点文件中的最佳权重?

Is there a way to reload the weights from a certain epoch or the best weights from the model checkpoint files created by ModelCheckpoint once the training is over?

我已经训练了 10 个 epoch 并创建了一个检查点，该检查点仅在每个 epoch 之后保存权重.最后一个 epoch 的 val_categorical_accuracy 比 epoch no 低一点.5. 我知道我应该设置 save_best_only=True 但我错过了.

I have trained that trained for 10 epochs and created a checkpoint that only saved weights after each epoch. The final epoch's val_categorical_accuracy is a bit lower than epoch no. 5. I know I should have set save_best_only=True but I missed that.

• 那么，现在有没有办法从最好的时代或第 5 个时代获得权重?
• 此外，ModelCheckpoint 是否在每个 epoch 之后覆盖权重检查点文件?

• So now, is there a way to get the weights from the best epoch or the epoch number 5?
• Also, does ModelCheckpoint overwrites weights after each epoch in the checkpoint file?

我有哪些选择?提前感谢您的帮助.

What are my options here? Thanks for your help in advance.

以下是我的实现:

checkpoint_path = 'saved_model/cp.ckpt'
checkpoint_dir = os.path.dirname(checkpoint_path)
print(checkpoint_dir)

lstm_model.fit(X_train_seq_pad, y_train_cat,
               epochs=100,
               validation_data=(X_val_seq_pad, y_val_cat),
               callbacks=[callbacks.EarlyStopping(monitor='val_loss', patience=3),
                          callbacks.ModelCheckpoint(filepath=checkpoint_path,
                                                    save_weights_only=True,
                                                    verbose=1)])

推荐答案

如果 filepath 不包含像 {epoch} 这样的格式选项，则 filepath 将被每个新的更好的模型覆盖.就您而言，这就是您无法在特定时期(例如时期 5)获得权重的原因.

If the filepath doesn't contain formatting options like {epoch} then filepath will be overwritten by each new better model. In your case, that's why you can't get the weight at a specific epoch (e.g epoch 5).

然而，您在这里的选择是在训练期间在 ModelCheckpoint 回调中选择格式化选项.比如

Your option here, however, is to choose the formatting option in the ModelCheckpoint callback during training time. Such as

tf.keras.callbacks.ModelCheckpoint(
                     filepath='model.{epoch:02d}-{val_loss:.4f}.h5', 
                     save_freq='epoch', verbose=1, monitor='val_loss', 
                     save_weights_only=True, save_best_only=False
                 )   

这将以不同但方便的方式在每个时期保存模型权重(以 .h5 格式).此外，如果我们将 save_best_only 选择为 True，它将以相同的方式保存最佳权重.

This will save the model weight (in .h5 format) at each epoch, in a different but convenient way. Additionally, if we choose save_best_only to True, it will save best weights in the same way.

代码示例

这是一个端到端工作示例供参考.我们将使用格式化选项以方便的方式保存每个时期的模型权重，我们将定义 filepath 参数如下:

Here is one end-to-end working example for reference. We will save model weights at each epoch in a convenient way with a formatting option that we will define the filepath parameter as follows:

img = tf.random.normal([20, 32], 0, 1, tf.float32)
tar = np.random.randint(2, size=(20, 1))

model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(10, input_dim = 32, activation= 'relu'))
model.add(tf.keras.layers.Dense(1, activation='sigmoid'))

callback_list = [
       tf.keras.callbacks.ModelCheckpoint(
            filepath='model.{epoch:02d}-{val_loss:.4f}.h5', 
            save_freq='epoch', verbose=1, monitor='val_loss', 
            save_weights_only=True, save_best_only=False
       )         
]
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(img, tar, epochs=5, verbose=2, validation_split=0.2,
          callbacks=callback_list)

它将在每个时期保存模型权重.我会在本地磁盘中找到所有权重.

It will save the model weight at each epoch. And I will find every weight in my local disk.

# model.epoch_number_score.h5
model.01-0.8022.h5
model.02-0.8014.h5
model.03-0.8005.h5
model.04-0.7997.h5
model.05-0.7989.h5

但是，请注意，我使用了 save_best_only = False，但是如果我们将其设置为 True，那么您只能以相同的方式获得最佳权重.像这样:

However, note that I used save_best_only = False, but If we set it to True, you then only get the best weight in the same way. Something like this:

# model.epoch_number_score.h5
model.01-0.8022.h5
model.03-0.8005.h5
model.05-0.7989.h5

这篇关于从 Tensorflow Keras 检查点重新加载最佳权重的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！