如何从预训练的ResNet模型Keras的图层中提取特征

由 cet发布于 2020-01-14 00:00:46

我使用Resnet3D训练了一个模型，我想提取一个层的神经元。我计划将它们与SVM分类器一起使用。如何提取这些权重并将其放入numpy数组？

通过keras加载权重

model = Resnet3DBuilder.build_resnet_18((128, 96, 96, 3), nClass[0])
model.load_weights('drive/app/models/3d_resnet_modelq.hdf5')

提取一层

dns = model.layers[-1].output

现在我该怎么办？

学乐容

2020-01-14 00:00:46

If you just want to visualise the features, in pure Keras you can define a Model with the desired layer as output:

from keras.models import Model

model_cut = Model(inputs=model.inputs, output=model.layers[-1].output)
features = model_cut.predict(x)  # Assuming you have your images in x

Note that in order for this to work, model must have been compiled at least once.

cet

这家伙很懒，什么都没留下

积分
0
话题
0
评论
3313
注册排名
1500