Dmitrii Milevich

Заметил, что функция normalized() для интерпретации не нормализует некоторые слова в творительном падеже, например 'утром', 'вечером'. Это вероятно связано со спецификой работы токенизатора. `list(TOKENIZER('утром'))` [MorphToken( value='утром', span=[0, 5), type='RU', forms=[Form('утром',...

Training custom classifier

1

Hello, I've seen your code at the front page for training a language model ``` `from fastai.text import * import multifit exp = multifit.from_pretrained("name of the model") fa_config = exp.pretrain_lm.tokenizer.get_fastai_config(add_open_file_processor=True)...

Specifying a validation set

1

I'm training a language model similar to what has been shown here https://github.com/n-waves/multifit/blob/master/notebooks/CLS-JA.ipynb While running `cls_dataset.load_clas_databunch(bs=exp.finetune_lm.bs).show_batch()` I'm getting this output > Running tokenization: 'lm-notst' ... > Validation set not found...

How to run YOLO on multiple images and save predictions to a txt file

47

Demonstration of YOLO is impressive! However, I'm wondering if there is a way to get predictions for a batch of images, say from a given directory, and save the names...

Inconsistent requirements

2

Please update the requirements.txt file. Right now it contains inconsistent dependencies that does not allow seamless installation through `pip install -r requreiemtns.txt`