loss is nan - Githubissues

fungtion / DANN

pytorch implementation of Domain-Adversarial Training of Neural Networks

MIT License

841 stars 151 forks source link

loss is nan #5

Closed houchenyu closed 5 years ago

houchenyu commented 5 years ago

When I run the main.py, output results show that three types of loss: err_s_label, err_s_domain, err_t_domain, become nan after several iterations. Anything wrong?