Open lincoln0211 opened 1 year ago
Same question. the results reported in Tables 1, 2, and 3 of the paper obtained using normalized weights? Or are they achievable using unnormalized weights?
We trained models with unnormalized weights. Increasing the learning rate can be an alternative of using normalized weights.
Thank you for your prompt response!
Thanks for your work.
I have one questions for training p2-weighting. How can I find the normalized weight part in the code like it is in the paper? Are the results in the paper indicative of unnormalized weights?
Thanks again and look forward to your reply.