我想使用tf.keras(tensorflow 2.3)对efficientnet进行微调,但我无法正确更改层的训练状态。
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"])
这样做是为了使我的随机重量的自定义顶部不会破坏的重量尽快。
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
在此之前,一切似乎都正常,我训练了我的模型两个时期,然后我想开始微调efficientnet基数,因此我调用
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了摘要,发现不可训练的权重数量保持不变,而且拟合并没有带来比保持冻结更好的结果。
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
,但这也没有效果。
可能是因为我同时使用了顺序模型和函数模型吗?
1条答案
按热度按时间kzipqqlq1#
对我来说,问题是在模型的一部分使用了顺序API。当我改为顺序API时,我的model.sumary()显示了所有的子层,并且可以将其中一些设置为可训练的,而另一些则不可以。