Gareth Booth Gareth001
iridiumblue
/ AttentionWithContext.py
Last active
October 5, 2020 17:16
— forked from cbaziotis/AttentionWithContext.py
Keras Layer that implements an Attention mechanism, compatible with Eager Execution and TF 1.13. Supports Masking. Follows the work of Yang et al. [https://www.cs.cmu.edu/~diyiy/docs/naacl16.pdf] "Hierarchical Attention Networks for Document Classification"
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # AttentionWithContext adapted for Tensorflow 1.13 with Eager Execution. | |
| # IMPORTANT -you can't use regular keras optimizers. You need to grab one that is subclassed from | |
| # tf.train.Optimizer. Not to worry, your favorite is probably there, for example - | |
| # https://www.tensorflow.org/api_docs/python/tf/train/AdamOptimizer | |
| # That's it, now you can use this layer - | |
| # Adapted from https://gist.github.com/cbaziotis/7ef97ccf71cbc14366835198c09809d2 | |
| # Tested using functional API. Just plop on top of an RNN, like so - |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import tensorflow as tf | |
| from tensorflow.python.platform import gfile | |
| with tf.Session() as sess: | |
| model_filename ='PATH_TO_PB.pb' | |
| with gfile.FastGFile(model_filename, 'rb') as f: | |
| graph_def = tf.GraphDef() | |
| graph_def.ParseFromString(f.read()) | |
| g_in = tf.import_graph_def(graph_def) | |
| LOGDIR='/logs/tests/1/' | |
| train_writer = tf.summary.FileWriter(LOGDIR) |