Hi, I have created the following optimizer. optimizer = optim.SGD(model.parameters(), lr=learning_rate, momentum=momentum) Based on a condition, I am updating the weights for the new inputs. Whenever I update the weight, I am running through the following code body. optimizer = optim.SGD(model.p…

This should help. I had a similar question recently… [image] Clarification on re-initializing optimizer in every epoch You shouldn’t be doing that, right? fmi as well as my issue here

Optimizer in PyTorch

vision

shubhvachher (Shubh Vachher) June 28, 2019, 11:17am 9

This should help. I had a similar question recently…

1 Like