experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
rei/fork-r2.3
STT-tensorflow/tensorflow/examples/image_retraining
History
A. Unique TensorFlower 1a36eb1550 Replace examples/image_retraining by a pointer to TensorFlow Hub. 
https://github.com/tensorflow/hub/tree/master/examples/image_retraining
has the same tool, upgraded to use TensorFlow Hub instead of raw graph defs.

PiperOrigin-RevId: 192502469
2018-04-11 13:53:23 -07:00
..
README.md Replace examples/image_retraining by a pointer to TensorFlow Hub. 2018-04-11 13:53:23 -07:00

README.md

NOTE: This code has moved to https://github.com/tensorflow/hub/tree/master/examples/image_retraining

retrain.py is an example script that shows how one can adapt a pretrained network for other classification problems (including use with TFLite and quantization).

As of TensorFlow 1.7, it is recommended to use a pretrained network from TensorFlow Hub, using the new version of this example found in the location above, as explained in TensorFlow's revised image retraining tutorial.

Older versions of this example (using frozen GraphDefs instead of TensorFlow Hub modules) are available in the release branches of TensorFlow versions up to and including 1.7.