Implementation of paper: Making Deep Neural Network Robust to Label Noise: a Loss Correction Approach.
- Python 2.7
- TensorFlow 1.4
- Train all models and evaluate all the tests with:
python experiment_mnist.py, or with
bash script/run_experiment_mnistfor faster training and testing. When this is finished, 4 files named
forward_t.npyshould have been created under the path
- Show the result with: