API symbolsoptim
Copy
AdamW
- class tensorplay.optim.adamw.AdamW(params, lr=0.001, betas=(0.9, 0.999), eps=1e-08, weight_decay=0.01, amsgrad=False, *, maximize=False, foreach=None, capturable=False, differentiable=False, fused=None)[source]
Adam with decoupled weight decay, matching
torch.optim.AdamW.
Help improve this page
Found an error, an unclear step, or a missing example?
Was this page helpful?