- Install dependencies:
pip install -r requirements.txt
-
Donwload and extract data from Kaggle
-
Preprocess the data:
python preprocess_data.py <path-to-train.tsv> <path-to-dataset-folder>
- Run experiment with standard cross-entropy loss:
python run_experiments.py <path-to-dataset-folder>
Add --gpu
to train on GPU
- Run experiment with complement cross-entropy loss:
python run_experiments.py <path-to-dataset-folder> --use_cce
- Accuracy scores will appearn on screen. More details will be available in Tensorboard:
tensorboard --logdir=./runs