1

我想使用 tf.keras（tensorflow 2.3）微调效率网络，但我无法正确更改层的训练状态。我的模型如下所示：

data_augmentation_layers = tf.keras.Sequential([
 keras.layers.experimental.preprocessing.RandomFlip("horizontal_and_vertical"),
 keras.layers.experimental.preprocessing.RandomRotation(0.8)])

efficientnet = EfficientNetB3(weights="imagenet", include_top=False,
                                input_shape=(*img_size, 3))

#Setting to not trainable as described in the standard keras FAQ
efficientnet.trainable = False

inputs = keras.layers.Input(shape=(*img_size, 3))
augmented = augmentation_layers(inputs)
base = efficientnet(augmented, training=False)
pooling = keras.layers.GlobalAveragePooling2D()(base)
outputs = keras.layers.Dense(5, activation="softmax")(pooling)

model = keras.Model(inputs=inputs, outputs=outputs)

model.compile(loss="categorical_crossentropy", optimizer=keras_opt, metrics=["categorical_accuracy"])

这样做是为了让我在自定义顶部的随机权重不会尽快破坏权重。

    Model: "functional_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_2 (InputLayer)         [(None, 512, 512, 3)]     0         
_________________________________________________________________
sequential (Sequential)      (None, 512, 512, 3)       0         
_________________________________________________________________
efficientnetb3 (Functional)  (None, 16, 16, 1536)      10783535  
_________________________________________________________________
global_average_pooling2d (Gl (None, 1536)              0         
_________________________________________________________________
dense (Dense)                (None, 5)                 7685      
=================================================================
Total params: 10,791,220
Trainable params: 7,685
Non-trainable params: 10,783,535

到目前为止，一切似乎都有效。我训练我的模型 2 个 epoch，然后我想开始微调效率网络基础。因此我打电话

for l in model.get_layer("efficientnetb3").layers:
  if not isinstance(l, keras.layers.BatchNormalization):
    l.trainable = True

model.compile(loss="categorical_crossentropy", optimizer=keras_opt, metrics=["categorical_accuracy"])

我重新编译并再次打印摘要，以查看不可训练权重的数量保持不变。拟合也不会带来比保持冷冻更好的效果。

 dense (Dense)                (None, 5)                 7685      
    =================================================================
    Total params: 10,791,220
    Trainable params: 7,685
    Non-trainable params: 10,783,535

Ps：我也试过efficientnet3.trainable = True了，但也没有效果。

难道这与我同时使用顺序模型和函数模型有关吗？

4

0 回答 0