从 CNN Keras 中提取迁移学习输出

Question

如何获取中间迁移学习输出。？例如：

from keras.models import Sequential
from keras.layers import Dense
# ... Other Imports..

from tensorflow.keras.applications.resnet50 import ResNet50
model = Sequential()
resnet = ResNet50(include_top = False, pooling = 'avg', weights = 'imagenet')
model.add(resnet)
model.add(Dense(10, activation = 'softmax'))
model.layers[0].trainable = False

尝试过：

layer_output=model.get_layer('resnet').output
layer_output=model.get_layer('resnet').output
intermediate_model=tf.keras.models.Model(inputs=model.input,outputs=layer_output)

Answer 1

Tensorflow 中有一个关于此问题的未解决 issue。根据issue，你需要同时传入outer model和inner model的输入，才能得到inner model的输出。

import numpy as np

layer_output = model.get_layer("resnet50").output
intermediate_model = tf.keras.models.Model(inputs=[model.input, resnet.input], outputs=[layer_output])

input_data = np.random.rand(1, 224, 224, 3)
result = intermediate_model.predict([input_data, input_data])

print(result[0].shape)

(7, 7, 2048)

从 CNN Keras 中提取迁移学习输出

Extracting Transfer learning output from CNN Keras

python

keras

conv-neural-network

tf.keras