Closed tommylau-exe closed 4 years ago
Prematurely updated model, undone with latest force-push
Updated model so that Tokenization file (tokenizer.json
) is accurate.
Predicted Low-Calorie | Predicted Average-Calorie | Predicted High-Calorie | |
---|---|---|---|
Actual Low-Calorie | 11096 | 1601 | 648 |
Actual Average-Calorie | 1673 | 12788 | 2264 |
Actual High-Calorie | 782 | 2298 | 21196 |
Updated model due to further tokenization changes.
Predicted Low-Calorie | Predicted Average-Calorie | Predicted High-Calorie | |
---|---|---|---|
Actual Low-Calorie | 11185 | 1590 | 609 |
Actual Average-Calorie | 1612 | 13053 | 2166 |
Actual High-Calorie | 657 | 2471 | 21003 |
Fixes #36
Perform text vectorization processes externally from Tensorflow.