Implementation of some unbalanced loss for NLP task like focal_loss, dice_loss, DSC Loss, GHM Loss et.al and adversarial training like FGM, FGSM, PGD, FreeAT.

Here is a loss implementation repository included unbalanced loss

You can find all the loss usage information in test_loss.py.

Here is a simple demo of usage:

import torch
from unbalanced_loss.focal_loss import MultiFocalLoss

batch_size, num_class = 64, 10
Loss_Func = MultiFocalLoss(num_class=num_class, gamma=2.0, reduction='mean')

logits = torch.rand(batch_size, num_class, requires_grad=True)  # (batch_size, num_classes)
targets = torch.randint(0, num_class, size=(batch_size,))  # (batch_size, )

loss = Loss_Func(logits, targets)
loss.backward()

Here is a Summary of Adversarial Training implementation.
you can find more details in adversarial_training/README.md

You can find a simple demo for bert classification in test_bert.py.

Here is a simple demo of usage:
You just need to rewrite train function according to input for your model in file PGD.py, then you can use adversarial training like below.

import transformers
from model import bert_classification
from adversarial_training.PGD import PGD

batch_size, num_class = 64, 10
# model = your_model()
model = bert_classification()
AT_Model = PGD(model)
optimizer = transformers.AdamW(model.parameters(), lr=0.001)

# rewrite your train function in pgd.py
outputs, loss = AT_Model.train_bert(token, segment, mask, label, optimizer)

here are some results tested on THNews classification task based on bert.
you can find run the code as below:

cd scripts
sh run_at.sh