Replace the print function by a file output function. #72
Conversation
This file contains 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
Signed-off-by: Norman Heckscher <[email protected]>
Signed-off-by: Norman Heckscher <[email protected]>
Need to complete refactor on this code. Still getting some warnings. WARNING:tensorflow:From /Users/norman/Documents/workspace/word-rnn-tensorflow/model.py:66: concat (from tensorflow.python.ops.array_ops) is deprecated and will be removed after 2016-12-14. Instructions for updating: This op will be removed after the deprecation date. Please switch to tf.concat_v2(). Signed-off-by: Norman Heckscher <[email protected]>
add log_dir argument
Signed-off-by: Norman Heckscher <[email protected]>
Signed-off-by: Norman Heckscher <[email protected]> # Conflicts: # train.py
Deprecated tf.concat operator. Please switch to use tf.concat_v2 for now. In the Beta release, we will update tf.concat to match argument order of `tf.concat_v2. Signed-off-by: Norman Heckscher <[email protected]>
Signed-off-by: Norman Heckscher <[email protected]> Remove blank lines Signed-off-by: Norman Heckscher <[email protected]>
Signed-off-by: Norman Heckscher <[email protected]>
revert concat_v2 Signed-off-by: Norman Heckscher <[email protected]>
Beam search is now only invoked once (as opposed to being called per word) and invokes the RNN to determine the probabilities and next state.
Most crucially, the `beam_search_predict` function was unnecessarily finding the mapped word.
better reflect loading rather than storing when sampling.
easier reading.
Changes to Tensorflow at the head neccesitate the need to create new instances of the RNNCell if using a different set of weights. In May 2017, Tensorflow will start transitioning this cell's behavior to use existing stored weights, if any, when it is called with scope=None (which can lead to silent model degradation).
Instead of printing the result of the sample, it will save its result into an output.txt file. Note: It append the result into the file, so content must be deleted from the file before running a second time.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Just learned how to do a pull request.
You can modify it. It does works on my setup, which should be a standard Windows 8.1 setup.