从预训练模型、迁移学习、tensorflow (load_model) 中移除顶层

Question

我已经用两个类预训练了一个模型（我自己保存的模型），我想将其用于迁移学习以训练一个具有六个类的模型。我已将预训练模型加载到新训练脚本中：

base_model = tf.keras.models.load_model("base_model_path")

如何删除 top/head 层（conv1D 层）？

我看到在 keras 中可以使用 base_model.pop()，对于 tf.keras.applications 可以简单地使用 include_top=false 但是使用 tf.keras 和 load_model 时有类似的东西吗？

（我试过这样的事情：

for layer in base_model.layers[:-1]:
    layer.trainable = False`

然后将其添加到新模型（？）但我不确定如何继续）

感谢您的帮助！

Answer 1

您可以尝试这样的操作：

基础模型由一个简单的 Conv1D 网络组成，输出层有两个类:

import tensorflow as tf

samples = 100
timesteps = 5
features = 2
classes = 2
dummy_x, dummy_y = tf.random.normal((100, 5, 2)), tf.random.uniform((100, 1), maxval=2, dtype=tf.int32)

base_model = tf.keras.Sequential()
base_model.add(tf.keras.layers.Conv1D(32, 3, activation='relu', input_shape=(5, 2)))
base_model.add(tf.keras.layers.GlobalMaxPool1D())
base_model.add(tf.keras.layers.Dense(32, activation='relu'))
base_model.add( tf.keras.layers.Dense(classes, activation='softmax'))

base_model.compile(optimizer='adam', loss = tf.keras.losses.SparseCategoricalCrossentropy())
print(base_model.summary())
base_model.fit(dummy_x, dummy_y, batch_size=16, epochs=1)
base_model.save("base_model")
base_model = tf.keras.models.load_model("base_model")

Model: "sequential_8"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 conv1d_31 (Conv1D)          (None, 3, 32)             224       
                                                                 
 global_max_pooling1d_13 (Gl  (None, 32)               0         
 obalMaxPooling1D)                                               
                                                                 
 dense_17 (Dense)            (None, 32)                1056      
                                                                 
 dense_18 (Dense)            (None, 2)                 66        
                                                                 
=================================================================
Total params: 1,346
Trainable params: 1,346
Non-trainable params: 0
_________________________________________________________________
None
7/7 [==============================] - 0s 3ms/step - loss: 0.6973
INFO:tensorflow:Assets written to: base_model/assets

新模型也是由一个简单的 Conv1D 网络组成，但输出层有六个类。它还包含 base_model 的所有层，除了第一个 Conv1D 层和最后一个输出层：

classes = 6
dummy_x, dummy_y = tf.random.normal((100, 5, 2)), tf.random.uniform((100, 1), maxval=6, dtype=tf.int32)
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv1D(64, 3, activation='relu', input_shape=(5, 2)))
model.add(tf.keras.layers.Conv1D(32, 2, activation='relu'))
for layer in base_model.layers[1:-1]: # Skip first and last layer
  model.add(layer)
model.add(tf.keras.layers.Dense(classes, activation='softmax'))
model.compile(optimizer='adam', loss = tf.keras.losses.SparseCategoricalCrossentropy())
print(model.summary())
model.fit(dummy_x, dummy_y, batch_size=16, epochs=1)

Model: "sequential_9"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 conv1d_32 (Conv1D)          (None, 3, 64)             448       
                                                                 
 conv1d_33 (Conv1D)          (None, 2, 32)             4128      
                                                                 
 global_max_pooling1d_13 (Gl  (None, 32)               0         
 obalMaxPooling1D)                                               
                                                                 
 dense_17 (Dense)            (None, 32)                1056      
                                                                 
 dense_19 (Dense)            (None, 6)                 198       
                                                                 
=================================================================
Total params: 5,830
Trainable params: 5,830
Non-trainable params: 0
_________________________________________________________________
None
7/7 [==============================] - 0s 3ms/step - loss: 1.8069
<keras.callbacks.History at 0x7f90c87a3c50>

从预训练模型、迁移学习、tensorflow (load_model) 中移除顶层

Remove top layer from pre-trained model, transfer learning, tensorflow (load_model)

python

tensorflow

keras

tf.keras

transfer-learning