Incorrect params initialization in AGC
haigh1510 opened this issue · comments
haigh1510 commented
Vaibhav Balloli commented
Thanks for bringing it up, not sure how I missed that.
NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch. Find explanation at tourdeml.github.io/blog/
haigh1510 opened this issue · comments
Thanks for bringing it up, not sure how I missed that.