pytorch-lr-finder
pytorch-lr-finder copied to clipboard
davidtvs
A learning rate range test implementation in PyTorch
I am training a multilingual-bert model for a sentiment classification task. My torch dataset returns a dictionary. I tried to run `lr_finder.range_test(....)` with and without `TrainDataLoaderIter` but I get the...
I try to use: ```ruby class CustomTrainIter(TrainDataLoaderIter): def inputs_labels_from_batch(self, batch_data): return batch_data["img"], batch_data["target"] ``` to work with DataLoader for the lr_finder.range_test() but still got the error: TypeError: list indices must...
Hey hey :wave: PyTorch now has it's native amp module for a while now https://pytorch.org/docs/stable/amp.html it would be great to move to that, or at least prefer using it if...
i want to be able to pull the value of steepest gradiant and use it in my code as a integer value. i see in the code it is under...
I am in need of a tool like this for a particular problem that is very sensitive to the LR. I am, however, unable to get this package to work...
In general, I need some wrappers about how batch prcessed and data flow to model.
My Code is here I am facing the following error. I want to ask one more thing Does LR Finder doesn't work for DataParallel? I have commented on the scheduler...
Please make it possible to return the best learning rate without making a plot. I suggest you refactor some code and pull the calculation of statistics out of the plotting...
Hello, It could be good to update the `LRFinder` object so to allow custom final activations to be computed before the loss. I changed this locally in my site-packages directory...
Here's the PR for the issue I created yesterday. Feel free to check it out or discard it as you please. Thank you again for your work.