2

当我运行我model(training=False)的 with 时batch_size = 2，模型使用 BatchNorm 的训练参数，但是当我运行 model with 时batch_size = 1，我的模型不使用训练过的参数，InstanceNorm实际上是这样做的。如何使用batch_size = 1as运行模型batch_size = 2？

class ContextExtractor(tf.keras.Model):
        def __init__(self, model_name, pretrained_shape):
            super().__init__()
            self.model = self.__get_model(model_name, pretrained_shape)

        def call(self, x, training=False, **kwargs):
            features = self.model(x, training=training)
            return features

        def __get_model(self, model_name, pretrained_shape):
            if model_name == "mobilenetv2":
                return MobileNetV2(input_shape=pretrained_shape,
                                   weights='imagenet',
                                   alpha=0.35,
                                   include_top=False,
                                   pooling='avg')

context_extractor = ContextExtractor("mobilenetv2", (224, 224, 3))
bc = tf.random.uniform((10, 224, 224, 3))

a1 = context_extractor(bc, training=False)
print(hash(a1[0].numpy().tobytes()))
# -8545286774071995675
a2 = context_extractor(bc[:2], training=False)
print(hash(a2[0].numpy().tobytes()))
# -8545286774071995675 <-- the same

a3 = context_extractor(bc[:1], training=False)
print(hash(a3[0].numpy().tobytes()))
# 8191470914604248680 <-- another result!

4

0 回答 0