Tensorflow: How can I extract image features from a specific layer of a pre-trained CNN?

Question

I have a pre-trained CNN model as a .pb file. I can load the model and extract the final vector from the last layer for all images. Now I would like to extract the vector coming from a specific layer and not the final for my images. I am using an import_graph_def function to load the model and I don't know the names of the layers because .pb file is large and I can't open it.

How can I run one part of the model and not the whole in order to get vectors until the layer I want?

Answer 1

One approach other than what was mentioned by Peter Hawkins, to use tf.Graph.get_operations() in the comments is to use tensorboard to find the name of the layer you would like to extract from.

From there you can just use

graph.get_tensor_by_name("import/layer_name")

to extract out whichever features you want.