Deploy tensorflow graphs for fast evaluation and export to tensorflow-less environments running numpy

tfdeploy logo

Build Status Documentation Status Package Status

Deploy tensorflow graphs for fast evaluation and export to tensorflow-less environments running numpy.

Now with tensorflow 1.0 support.

Evaluation usage
import tfdeploy as td
import numpy as np

model = td.Model("/path/to/model.pkl")
inp, outp = model.get("input", "output")

batch = np.random.rand(10000, 784)
result = outp.eval({inp: batch})
Installation and dependencies

 

 

 

To finish reading, please visit source site