You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Yes, you are right:) I'll use English to reply for possible inspirations to everyone.
"how to understand magic_model?" -- It's for running a specified model (e.g., BERT) whose parameters are the sum of multiple sets of parameters (e.g., \theta + \theta'(\phi)) while we don't need to re-write the original forward() function. Our implementation is a bit like a hack to PyTorch.Module. If you have better ways to do it, please let me know.
"why can dev_loss.backward() update the Generator weight?" -- In the code, the route of gradient propagation is dev_loss (classifier.p::Line154) -> deltas (Line 147) -> grads (Line 140) -> aug_probs (Line 119) -> generator parameters (via gumbel_softmax, generator.py::Line104). For the correspondence between our paper and code, please refer to this.
Sorry that I don't quite understand your question "这里是用到了前一次classifer到梯度了吗". Could you specify it more detailedly?
how to understand magic_model
why augmentation.classifier line 158 dev_loss.backward() can update the Generator weight
The text was updated successfully, but these errors were encountered: