如何使用嵌套模型显示 Tensorflow 模型中的所有层？

Question

如何使用模型库显示 tensorflow 模型中的所有图层？

base_model = keras.applications.MobileNetV3Small(
    input_shape=model_input_shape,
    include_top=False,
    weights="imagenet",
)

# =================== build model
model = keras.Sequential(
    [
        keras.Input(shape=image_shape),
        preprocessing.Resizing(*model_input_shape[:2]),
        preprocessing.Rescaling(1.0 / 255),
        base_model,
        layers.GlobalAveragePooling2D(),
        # missing dropout
        layers.Dense(1, activation="sigmoid"),
    ]
)

model.summary()

输出是这样的：

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
resizing (Resizing)          (None, 224, 224, 3)       0         
_________________________________________________________________
rescaling_1 (Rescaling)      (None, 224, 224, 3)       0         
_________________________________________________________________
MobilenetV3small (Functional (None, 7, 7, 1024)        1529968    <---------- why can't I see all layers here?
_________________________________________________________________
global_average_pooling2d (Gl (None, 1024)              0         
_________________________________________________________________
dense (Dense)                (None, 1)                 1025

如何显示所有图层？

for layer in model.layers:
    print(layer)

上面也有同样的问题。我做错了什么？

Answer 1

在这样的设置中，base_model 充当单层，即。成为嵌套。要检查它，您可以尝试

model.layers[2].summary()


for i, layer in enumerate(model.layers):
    if i == 2:
        for nested_layer in layer.layers:
            print(nested_layer)

或者，更直观地说，您可以使用 this solution.

def summary_plus(layer, i=0):
    if hasattr(layer, 'layers'):
        if i != 0: 
            layer.summary()
        for l in layer.layers:
            i += 1
            summary_plus(l, i=i)
summary_plus(model)

或者，您也可以使用plot_model功能

keras.utils.plot_model(
    model,
    expand_nested=True # < make it true 
)

更新 1：就此问题提出。 Keras #15239。希望能尽快解决。

更新 2：model.summary 现在有 expand_nested 参数。 #15251

如何使用嵌套模型显示 Tensorflow 模型中的所有层？

How to show all layers in a Tensorflow model with nested model?

deep-learning

keras

tensorflow

tensorflow2.0