caprone

but pre-trained model works really???

1

I need a model only for inference but your Best 5 epch model is really poor...

HI, sorry but your grammar model is very weak on real cases

4

HI I tested on some simple sentences, like: args = TTSettings(num_beams=5, min_length=1, max_length=5000) happy_grammar = HappyTextToText("T5", "vennify/t5-base-grammar-correction") result = happy_grammar.generate_text('This mvie did everUthing a van dqmme mLvie shoHld do Ahich...

HI surprisingly your combo fails with unbalanced data...probably because You 'split_datasets' function in classifier_stacking module can't handle stratified splitting; in real world task heavily unbalanced data occurs very often;

HI is it possible to evaluate on a custom images-dataset?

doesn't catch some propocessing error of skelarn

4

"ValueError: Minimum of desired feature range must be smaller than maximum. Got (0.0, 0.0)." after useless 3 hours of training on a very smaller dataset...too slow a, not verbose...and bugged

seems don't run on GPU??

1

HI i'm try to train a base model, but seems does't works with GPU?..is very slow and no output from (verbose =True)... any idea? Thanks