tf.keras.callbacks.ModelCheckpoint忽略monitor参数，一直使用loss

Question

我运行 tf.keras.callbacks.ModelCheckpoint 具有准确度指标，但损失用于保存最佳检查点。我在不同的地方（我的电脑和协作）和两个不同的代码测试过这个并面临同样的问题。这是一个示例代码和结果：

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
import os
import shutil

def get_uncompiled_model():
    inputs = keras.Input(shape=(784,), name="digits")
    x = layers.Dense(64, activation="relu", name="dense_1")(inputs)
    x = layers.Dense(64, activation="relu", name="dense_2")(x)
    outputs = layers.Dense(10, activation="softmax", name="predictions")(x)
    model = keras.Model(inputs=inputs, outputs=outputs)
    return model

def get_compiled_model():
    model = get_uncompiled_model()
    model.compile(
        optimizer="rmsprop",
        loss="sparse_categorical_crossentropy",
        metrics=["accuracy"],
    )
    return model

(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()

# Preprocess the data (these are NumPy arrays)
x_train = x_train.reshape(60000, 784).astype("float32") / 255
x_test = x_test.reshape(10000, 784).astype("float32") / 255

y_train = y_train.astype("float32")
y_test = y_test.astype("float32")

# Reserve 10,000 samples for validation
x_val = x_train[-10000:]
y_val = y_train[-10000:]
x_train = x_train[:-10000]
y_train = y_train[:-10000]


ckpt_folder = os.path.join(os.getcwd(), 'ckpt')
if os.path.exists(ckpt_folder):
    shutil.rmtree(ckpt_folder)

ckpt_path = os.path.join(r'D:\deep_learning\tf_keras\semantic_segmentation\logs', 'mymodel_{epoch}')


callbacks = [
    tf.keras.callbacks.ModelCheckpoint(
        # Path where to save the model
        # The two parameters below mean that we will overwrite
        # the current checkpoint if and only if
        # the `val_loss` score has improved.
        # The saved model name will include the current epoch.
        filepath=ckpt_path,
        montior="val_accuracy",
        # save the model weights with best validation accuracy
        mode='max',
        save_best_only=True,  # only save the best weights
        save_weights_only=False,
        # only save model weights (not whole model)
        verbose=1
    )
]

model = get_compiled_model()


model.fit(
    x_train, y_train, epochs=3, batch_size=1, callbacks=callbacks, validation_split=0.2, steps_per_epoch=1
)

1/1 [==============================] - ETA：0s - 损失：2.6475 - 准确性: 0.0000e+00 Epoch 1：val_loss 从 -inf 改进到 2.32311，将模型保存到 D:\deep_learning\tf_keras\semantic_segmentation\logs\mymodel_1 1/1 [================================] - 6s 6s/步 - 损失：2.6475 - 精度：0.0000e+ 00 - val_loss: 2.3231 - val_accuracy: 0.1142

纪元 2/3 1/1 [==============================] - ETA：0s - 损失：1.9612 - 精度：1.0000 Epoch 2：val_loss 从 2.32311 改进到 2.34286，将模型保存到 D:\deep_learning\tf_keras\semantic_segmentation\logs\mymodel_2 1/1 [================================] - 5s 5s/步 - 损失：1.9612 - 精度：1.0000 - val_loss: 2.3429 - val_accuracy: 0.1187

时代 3/3 1/1 [==============================] - ETA：0s - 损失：2.8378 - 精度：0.0000e+00 Epoch 3：val_loss 没有从 2.34286 提高 1/1 [================================] - 5s 5s/步 - 损失：2.8378 - 精度：0.0000e+ 00 - val_loss: 2.2943 - val_accuracy: 0.1346

Answer 1

在你的代码中，你写 montior 而不是 monitor，函数没有这个词作为参数然后使用默认值，如果你像下面这样写，你会得到什么你想要：

callbacks = [
    tf.keras.callbacks.ModelCheckpoint(
        filepath=ckpt_path,
        monitor="val_accuracy",
        mode='max',
        save_best_only=True,
        save_weights_only=False,
        verbose=1
    )
]

tf.keras.callbacks.ModelCheckpoint忽略monitor参数，一直使用loss

tf.keras.callbacks.ModelCheckpoint ignores the montior parameter and always use loss

python

deep-learning

keras

tensorflow