Training classifiers via Debate
Note: This code is a work in progress. It will change, and hopefully get better, during the next few months.
On top of that we run additional experiment on MNIST as well as FashionMNIST data and train classifiers from debate results.
Install the python dependencies by running the following in a python 3.6
pip install -r requirements.txt
All code is located in the
- To train a judge use
- To run individual debates use
- To evaluate the accuracy of a judge combined with debate use
- To use debate to train a classifier use
sacred for tracking experiments. The results are typically stored in the
amplification_experiments folders. Scripts that use
sacred have parameters specified in a config function. To specify values for these parameters, use the
with statement, e.g.
python ai-safety-debate/run_debate.py with judge_path=ai-safety-debate/saved_models/mnist4