pytorch-lr-finder
pytorch-lr-finder copied to clipboard
LR finder for optimizing a single input tensor?
I have an optimization task that optimizes a single tensor by passing it through a set of transforms and then into the model. Losses are then calculated by using hooks attached to various model layers.
Is is possible to use this project for finding the optimal LR for my optimization task? The code looks like it requires a DataLoader instance.
A DataLoader is not strictly needed. It requires an instance of TrainDataLoaderIter and optionally ValDataLoaderIter.
You can implement classes that inherit from these and modify their behavior. The important thing is that the next method must return a pair of input, label which are then used for the forward pass and loss calculation.
Closing due to inactivity