List of tensor names in graph in Tensorflow

Question

The graph object in Tensorflow has a method called "get_tensor_by_name(name)". Is there anyway to get a list of valid tensor names?

If not, does anyone know the valid names for the pretrained model inception-v3 from here? From their example, pool_3, is one valid tensor but a list of all of them would be nice. I looked at the paper referred to and some of the layers seems to correspond to the sizes in table 1 but not all of them.

Answer 1

The paper is not accurately reflecting the model. If you download the source from arxiv it has an accurate model description as model.txt, and the names in there correlate strongly with the names in the released model.

To answer your first question, sess.graph.get_operations() gives you a list of operations. For an op, op.name gives you the name and op.values() gives you a list of tensors it produces (in the inception-v3 model, all tensor names are the op name with a ":0" appended to it, so pool_3:0 is the tensor produced by the final pooling op.)

Answer 2

The above answers are correct. I came across an easy to understand / simple code for the above task. So sharing it here :-

import tensorflow as tf  def printTensors(pb_file):      # read pb into graph_def     with tf.gfile.GFile(pb_file, "rb") as f:         graph_def = tf.GraphDef()         graph_def.ParseFromString(f.read())      # import graph_def     with tf.Graph().as_default() as graph:         tf.import_graph_def(graph_def)      # print operations     for op in graph.get_operations():         print(op.name)   printTensors("path-to-my-pbfile.pb")