Learning_From_Mistakes

Learning From Mistakes: A Multi-level Optimization Framework (Official Pytorch implementation for applications to Neural Architecture Search (NAS) and Data Reweighting (DR)).

The requiring environment is as bellow:

• Linux
• Python 3+
• PyTorch 1.8.1
• Torchvision 0.9.1

Here is an example about running the search stage of DARTS on CIFAR-10:

python train_search_lfm.py --is_cifar100 0 --gpu 0 --unrolled --save darts-cifar10

Here is an example about running the evaluation stage of architecture searched on CIFAR-10:

python train.py --gpu 0 --auxiliary --cutout --arch [searched architecture]

Here is an example about running the experiment on class imbalance dataset with 100 imbalance factor

python dr-lfm-imbalance.py --dataset cifar100 --num_classes 100 --imb_factor 0.01

Checkpoints of the Application to NAS:

• Evaluation checkpoints for DARTS on CIFAR-10
• Evaluation checkpoints for P-DARTS on CIFAR-10
• Evaluation checkpoints on ImageNet with architecture search by DARTS on CIFAR-10
• Evaluation checkpoints on ImageNet with architecture search by P-DARTS on CIFAR-10

Checkpoints of the Application to DR (Class Imbalance):

• Checkpoints for experiment on CIFAR-10 with 10 Imbalance Factor
• Checkpoints for experiment on CIFAR-10 with 20 Imbalance Factor
• Checkpoints for experiment on CIFAR-10 with 50 Imbalance Factor
• Checkpoints for experiment on CIFAR-10 with 100 Imbalance Factor
• Checkpoints for experiment on CIFAR-10 with 200 Imbalance Factor
• Checkpoints for experiment on CIFAR-100 with 10 Imbalance Factor
• Checkpoints for experiment on CIFAR-100 with 20 Imbalance Factor
• Checkpoints for experiment on CIFAR-100 with 50 Imbalance Factor
• Checkpoints for experiment on CIFAR-100 with 100 Imbalance Factor
• Checkpoints for experiment on CIFAR-100 with 200 Imbalance Factor

Checkpoints of the Application to DR (Label Noisy):

• Checkpoints for experiment on CIFAR-10 with 0.2 Flip Noisy
• Checkpoints for experiment on CIFAR-10 with 0.4 Flip Noisy
• Checkpoints for experiment on CIFAR-100 with 0.2 Flip Noisy
• Checkpoints for experiment on CIFAR-100 with 0.4 Flip Noisy