graph

Tensorflow Quantizaiton

On: October 8, 2019

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

During inference, precision in floats is not needed and can be reduced to using 8 bits instead of 32 bits this allows to bin continuous values to discrete ranges, and therefore is known as Quantization. This enables us to increase the bandwith sent (or increase the memory footprint in caseContinue Reading

Tensorflow – Graph Freezing

On: October 2, 2019

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

In prediction/inference mode, variable types are unnecessary, so by freezing the graph we convert all variables in a graph and checkpoint into constants. Also there are structure nodes and operations related to training that we don’t need and can be removed by the freezing process as well. The freezing processContinue Reading