Tensorflow - 使用sample_weight自定义损失函数

Question

我正在尝试运行一个接受样本权重的自定义函数。我正在遵循这份文档https://www.tensorflow.org/api_docs/python/tf/keras/losses/Loss。

然而，当我尝试使用以下损失函数时：

class deltaE(Loss):
  def __call__(self, y_true, y_pred, sample_weight):
    errors = tf_get_deltaE2000(y_true * tf_Xtrain_labels_max, y_pred * tf_Xtrain_labels_max)
    errors *= sample_weight
    return tf.math.reduce_mean(errors, axis=-1)

loss_deltaE = deltaE()

我在使用 Model.fit 方法时遇到了这个错误。

TypeError: in user code:

    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:571 train_function  *
        outputs = self.distribute_strategy.run(
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:951 run  **
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica
        return fn(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:543 train_step  **
        self.compiled_metrics.update_state(y, y_pred, sample_weight)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:411 update_state
        metric_obj.update_state(y_t, y_p)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/metrics_utils.py:90 decorated
        update_op = update_state_fn(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/metrics.py:603 update_state
        matches = self._fn(y_true, y_pred, **self._fn_kwargs)

    TypeError: __call__() missing 1 required positional argument: 'sample_weight'

我正在使用一个生成器，它生成长度为 3 的元组，正如所需。我已经检查过了。这个工作很顺利。

成本函数也很好用。当我使用下面的代码时，模型会顺利地训练。

def loss_deltaE(y_true, y_pred):
  errors = tf_get_deltaE2000(y_true * tf_Xtrain_labels_max, y_pred * tf_Xtrain_labels_max)
  return tf.math.reduce_mean(errors, axis=-1)

如果有人有什么线索，我会非常感激。提前致谢！

- Rafael Toledo

---

你是否只需要使用Keras Loss方法的解决方案，还是其他方法也可以？ - Marco Cerliani

欢迎使用其他方法。 - Rafael Toledo

Answer 1

这是一种解决方案，用于向自定义损失函数传递额外的参数。技巧在于使用虚拟输入，有助于以正确的方式构建和使用损失函数。我提供了一个回归问题的虚拟示例。

def mse(y_true, y_pred, sample_weight):

    error = y_true-y_pred

    return K.mean(K.sqrt(error)*sample_weight)


X = np.random.uniform(0,1, (1000,10))
y = np.random.uniform(0,1, 1000)
W = np.random.uniform(1,2, 1000)

inp = Input((10))
true = Input((1))
sample_weight = Input((1))
x = Dense(32, activation='relu')(inp)
out = Dense(1)(x)

m = Model([inp,true, sample_weight], out)
m.add_loss( mse( true, out, sample_weight ) )
m.compile(loss=None, optimizer='adam')
history = m.fit([X, y, W], y, epochs=10)

# final fitted model to compute predictions
final_m = Model(inp, out)

- Marco Cerliani