python - Tensorflow 2.0 : custom keras metric caused tf. 函数回溯警告

Question

当我使用以下自定义指标(keras 样式)时:

from sklearn.metrics import classification_report, f1_score
from tensorflow.keras.callbacks import Callback

class Metrics(Callback):
    def __init__(self, dev_data, classifier, dataloader):
        self.best_f1_score = 0.0
        self.dev_data = dev_data
        self.classifier = classifier
        self.predictor = Predictor(classifier, dataloader)
        self.dataloader = dataloader

    def on_epoch_end(self, epoch, logs=None):
        print("start to evaluate....")
        _, preds = self.predictor(self.dev_data)
        y_trues, y_preds = [self.dataloader.label_vector(v["label"]) for v in self.dev_data], preds
        f1 = f1_score(y_trues, y_preds, average="weighted")
        print(classification_report(y_trues, y_preds,
                                    target_names=self.dataloader.vocab.labels))
        if f1 > self.best_f1_score:
            self.best_f1_score = f1
            self.classifier.save_model()
            print("best metrics, save model...")

我收到以下警告:

W1106 10:49:14.171694 4745115072 def_function.py:474] 6 out of the last 11 calls to .distributed_function at 0x14a3f9d90> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings is likely due to passing python objects instead of tensors. Also, tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. Please refer to https://www.tensorflow.org/beta/tutorials/eager/tf_function#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for more details.

Answer 1

当 TF 函数因其参数的形状或数据类型(对于张量)甚至值(Python 或 np 对象或变量)发生变化而被回溯时，会出现此警告。

在一般情况下，修复方法是在传递给 Keras 或 TF 某处的自定义函数的定义之前使用 @tf.function(experimental_relax_shapes=True) 。这会尝试检测并避免不必要的回溯，但不能保证解决问题。

就您而言，我猜 Predictor 类是一个自定义类，因此请将 @tf.function(experimental_relax_shapes=True) 放在 Predictor.predict() 的定义之前。