Tflite inference model #50
Merged
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
…ras and tflite models
Pull Request Test Coverage Report for Build 10534629730Details
💛 - Coveralls |
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Outdated suggestions cannot be applied.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.
closes #48 and #49
not completely convinced that the tflite models out-perform .keras models on predictions but they do on speed.
this changes formalises .keras as a default model type and .tflite as a good alternative for exploration.
haven't completely removed .h5 models as they are good for cross-platform and backwards compatibility.
all inference should now go through MDRNNInferenceModel sub-classes and the PredictiveMusicMDRNN could be renamed as "model builder" or some such as it's only necessary for building training or inference models from scratch.