TextClassificationBenchmark icon indicating copy to clipboard operation
TextClassificationBenchmark copied to clipboard

Saving and Loading saved models gives different results

Open joeybose opened this issue 5 years ago • 0 comments

Hi, There is a serious problem in the current codebase. If you save a model then reload it in a DIFFERENT time (not the same execution of main.py) the accuracy is 50% on IMDB. As a sanity check if you save and reload in the execution of main.py then there is no problem. If I had to guess this is a dataloading problem where there is a mistmatch between the saved model and the newly loaded model in a second execution.

joeybose avatar Apr 12 '19 15:04 joeybose