Tensorflow

On:
In: AI, Computer Vision, Deep Machine Learning, NLP, Reinforcement Learning

After training we can optimize a frozen graph or even a dynamic graph by removes training-specific and debug-specific nodes, fusing common operations, and removes code that isn’t used/reached. Code Example from tensorflow.python.tools import optimize_for_inference_lib inputGraph = tf.GraphDef() #read in a frozen model with tf.gfile.Open(‘frozentensorflowModel.pb’, “rb”) as f: data2read = f.read() inputGraph.ParseFromString(data2read) outputGraph = optimize_for_inference_lib.optimize_for_inference(inputGraph, [“inputTensor”],        Continue Reading