tensorflow: InvalidArgumentError 同时找到 AUC 分数

Question

我有一个标签为 0 和 1 的数据集，这是二元分类问题。尝试使用 tf.keras.metrics.AUC() 作为 model.compile(.. 函数中的指标来查找 AUC 分数时出错。

代码：

initializer = tf.keras.initializers.RandomUniform(minval=0., maxval=1.)

model = tf.keras.models.Sequential()
model.add(tf.keras.Input(shape=(2,)))
model.add(tf.keras.layers.Dense(4, activation='tanh', kernel_initializer=initializer))
model.add(tf.keras.layers.Dense(8, activation='tanh', kernel_initializer=initializer))
model.add(tf.keras.layers.Dense(16, activation='tanh', kernel_initializer=initializer))
model.add(tf.keras.layers.Dense(8, activation='tanh', kernel_initializer=initializer))
model.add(tf.keras.layers.Dense(4, activation='tanh', kernel_initializer=initializer))
model.add(tf.keras.layers.Dense(1))

model.compile(loss= tf.keras.losses.BinaryCrossentropy(),
                      optimizer = tf.optimizers.SGD(momentum=0.9,), 
            metrics=['accuracy', tf.keras.metrics.AUC()])

model.fit(X, y, validation_data=(X_val, y_val), epochs=10)

如果我从指标中删除 AUC，代码运行正常。

错误：

InvalidArgumentError: assertion failed: [predictions must be >= 0] [Condition x >= y did not hold element-wise:] [x (sequential_48/dense_293/BiasAdd:0) = ] [[2.12408257][2.12408257][-2.12408257]...] [y (Cast_10/x:0) = ] [0]
[[{{node assert_greater_equal/Assert/AssertGuard/else/_1/assert_greater_equal/Assert/AssertGuard/Assert}}]] [Op:__inference_train_function_120642]

Function call stack: train_function

如何找到 AUC score/how 以将 AUC 分数设置为编译中的指标？

Answer 1

您在最后一个致密层中缺少激活函数。如果我们默认不提及，它将考虑线性激活，这意味着您可以获得任何值，包括负值。

InvalidArgumentError: assertion failed: [predictions must be >= 0] [Condition x >= y did not hold element-wise:] [x (sequential_48/dense_293/BiasAdd:0) = ] [[2.12408257][2.12408257][-2.12408257]...]

If you can check above error, it is saying the same (i.e predictions for your model must be >=0), but your model return [[2.12408257][2.12408257][-2.12408257]...] values.

为避免这种情况，您应该将 sigmoid 激活函数添加到最后一个密集层，如下所示。

initializer = tf.keras.initializers.RandomUniform(minval=0., maxval=1.)
model = tf.keras.models.Sequential()
model.add(tf.keras.Input(shape=(2,)))
model.add(tf.keras.layers.Dense(4, activation='tanh', kernel_initializer=initializer))
model.add(tf.keras.layers.Dense(8, activation='tanh', kernel_initializer=initializer))
model.add(tf.keras.layers.Dense(16, activation='tanh', kernel_initializer=initializer))
model.add(tf.keras.layers.Dense(8, activation='tanh', kernel_initializer=initializer))
model.add(tf.keras.layers.Dense(4, activation='tanh', kernel_initializer=initializer))
model.add(tf.keras.layers.Dense(1, activation='sigmoid'))

model.compile(loss= tf.keras.losses.BinaryCrossentropy(),
                      optimizer = tf.optimizers.SGD(momentum=0.9,), 
            metrics=['accuracy', tf.keras.metrics.AUC()])

model.fit(X, y, validation_data=(X_val, y_val), epochs=10)

tensorflow: InvalidArgumentError 同时找到 AUC 分数

tensorflow: InvalidArgumentError while find the AUC score

python

auc

tensorflow

tensorflow2.0