Open rehohoho opened 3 years ago
Current difficulty: little support for subclassed models, have to apply quantization annotation recursively manually.
Think this is better done when tensorflow supports quantization aware training better. Moving to not urgent, since thermal issues is not that bad now.
Prerequisites
Please answer the following question for yourself before submitting an issue.
1. The entire URL of the file you are using
https://github.com/tensorflow/models/tree/master/official/vision/beta
2. Describe the feature you request
Add workflow for quantization aware training. Can reference from some available research implementations, but make sure it is based on https://www.tensorflow.org/model_optimization/guide/quantization/training_comprehensive_guide#define_quantization_aware_model
3. Additional context
May get major speedups (up to 4x) and allow running on NNAPI or hexagon delegate. https://www.tensorflow.org/lite/performance/delegates#delegates_by_model_type Tracking from whizzscooters/data-engine#114.
4. Are you willing to contribute it? (Yes or No)