Open trivedigaurav opened 4 years ago
It appears like run_clf_multihead.py expects test dataset to have gold standard labels. However, the csv in data/semeval/test.csv doesn't contain any labels. As a result, the script fails to generate metrics to reproducing the results mentioned here: https://github.com/NVIDIA/sentiment-discovery/blob/master/analysis/reproduction.md#finetuning-classifiers
It appears like run_clf_multihead.py expects test dataset to have gold standard labels. However, the csv in data/semeval/test.csv doesn't contain any labels. As a result, the script fails to generate metrics to reproducing the results mentioned here: https://github.com/NVIDIA/sentiment-discovery/blob/master/analysis/reproduction.md#finetuning-classifiers