A type estimator based on fine-tuning Google BERT
python transformer_analyser.py --train --train_csv "training_data.csv" --test_csv "testing_data.csv"
python transformer_analyser.py --pred --input_text "Of course I'll help\!"
You can monitor training progress using TensorBoard. To start it, run the following command:
tensorboard --logdir=./logs --reload_multifile True
Then, open your browser at http://localhost:6006/ to see the Dashboard.
When adding new libraries to the project, make your you keep environment.yml
updated.
To accomplish this, please run the following:
conda env export > environment.yml