Implementation of ULMFit algorithm for text classification via transfer learning
Implementation of ulmfit using basenet wrappers.
Code in ulmfit.py
is adapted directly from fastai code.
conda create -n ulm_env python=3.6 pip -y
source activate ulm_env
# pytorch
conda install pytorch pytorch=0.3.1 cuda90 -c pytorch -y
# spacy (for tokenization)
conda install -c conda-forge spacy -y
python -m spacy download en
# additional requirements
pip install -r requirements.txt
See ./run.sh
for usage.