diff options
author | A. Unique TensorFlower <gardener@tensorflow.org> | 2017-11-10 15:21:48 -0800 |
---|---|---|
committer | TensorFlower Gardener <gardener@tensorflow.org> | 2017-11-10 16:59:30 -0800 |
commit | cf0f384382d0c3645eb53cd27d38d15a9c3b28b5 (patch) | |
tree | 0460593dbdc4c9bca11fa6a9ccb7d51077d15678 /tensorflow/examples/image_retraining | |
parent | 070b06a8ab37c8aa0ee2cdd0cc12defd009bff9b (diff) |
Create documentation for retrain.py to describe addition of fixed point layer.
Add Readme file to tf.contrib.quantize to provide an overview of fake quantization
PiperOrigin-RevId: 175345154
Diffstat (limited to 'tensorflow/examples/image_retraining')
-rw-r--r-- | tensorflow/examples/image_retraining/README.md | 12 |
1 files changed, 12 insertions, 0 deletions
diff --git a/tensorflow/examples/image_retraining/README.md b/tensorflow/examples/image_retraining/README.md new file mode 100644 index 0000000000..8a49525c6e --- /dev/null +++ b/tensorflow/examples/image_retraining/README.md @@ -0,0 +1,12 @@ +retrain.py is an example script that shows how one can adapt a pretrained +network for other classification problems. A detailed overview of this script +can be found at: +https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/#0 + +The script also shows how one can train layers +with quantized weights and activations instead of taking a pre-trained floating +point model and then quantizing weights and activations. +The output graphdef produced by this script is compatible with the TensorFlow +Lite Optimizing Converter and can be converted to TFLite format. + + |