ResNet50() 不显示摘要和抛出错误

Question

inputs = tf.keras.layers.Input(shape=(32,32,3))
resize = tf.keras.layers.UpSampling2D(size=(7,7))(inputs)
feature_extractor = tf.keras.applications.resnet.ResNet50(input_shape=(224, 224,3),include_top=False,weights='imagenet')(resize)
feature_extractor.summary()

以上代码导致错误 AttributeError: 'KerasTensor' object has no attribute 'summary。

但是，如果我如下所示从 ResNet50() 中删除调整大小参数，它会无误地显示摘要。为什么？

tf.keras.applications.resnet.ResNet50(input_shape=(224, 224, 3),
                                               include_top=False,
                                               weights='imagenet')

Answer 1

这是因为您没有通过定义 tf.keras.models.Model 模型来完成构建模型。

inputs = tf.keras.layers.Input(shape=(32,32,3))
resize = tf.keras.layers.UpSampling2D(size=(7,7))(inputs)
feature_extractor = tf.keras.applications.resnet.ResNet50(input_shape=(224, 224,3),include_top=False,weights='imagenet')(resize)

model=tf.keras.models.Model(inputs,feature_extractor)
model.summary()

ResNet50() 不显示摘要和抛出错误

ResNet50() not displaying summary and throwing error

tensorflow

keras

transfer-learning