Dhanachandra Ningthoujam

Hi @ZhixiuYe Could please update the code to find the path_score? This part is still left in your implementation.

subprocess.CalledProcessError:

1

I got the following error: `[2022-01-13 14:47:32,154] [INFO] [launch.py:131:sigkill_handler] Killing subprocess 2273 Traceback (most recent call last): File "/home/ubuntu/anaconda3/envs/gpt2_lm/lib/python3.8/runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "/home/ubuntu/anaconda3/envs/gpt2_lm/lib/python3.8/runpy.py", line...

Training on TPU

1

How to train the GPT2-xl on TPU? And which TPU can be used to train? And what would be RAM size?

how to display PdfAnnotator object using matplotlib or cv2

2

```a = PdfAnnotator('a.pdf') a.add_annotation( 'square', Location(x1=50, y1=50, x2=100, y2=100, page=0), Appearance(stroke_color=(1, 0, 0), stroke_width=5), ) #something like plot.show(a)

How to reproduce the same model released by you

1

Hi, I tried training the same model with same [config.cfg](https://github.com/Legal-NLP-EkStep/legal_NER/blob/main/training/config.cfg) and [training data train.spacy](https://github.com/Legal-NLP-EkStep/legal_NER/blob/main/training/Combined_Data_Judgement_Preamble_spacy_format/train.spacyl) and [dev.spacy](https://github.com/Legal-NLP-EkStep/legal_NER/blob/main/training/Combined_Data_Judgement_Preamble_spacy_format/dev.spacy) files provided by you. But, I got lower results than your pretrain model (en_legal_ner_trf)....