pytorch-lr-finder

pytorch-lr-finder copied to clipboard

Thanks for providing this great package. Have you considered making a conda-forge recipe for it? That would help us a lot by making it easier to include in conda environment...

rabernat

how to get the best LR

2

Hi, I run the following code and got the following picture. I am wondering what the best LR is in my picture? how to print/display the best LR in the...

ardeal

'dict' object has no attribute 'param_groups'

5

I am facing the following error, any suggestions? py3.8.egg/torch_lr_finder/lr_finder.py", line 361, in _check_for_scheduler AttributeError: 'dict' object has no attribute 'param_groups' The code is a simple one lr_finder = LRFinder(models, optimizers,...

manza-ari

'<' not supported between instances of 'MSELoss' and 'int'

2

Using: lr_finder = LRFinder(model, optimizer, loss_fn) Get this error: '

RowanG1

LR finder for optimizing a single input tensor?

1

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...

ProGamerGov

device issue says its bool not torch.deivce but i have printed the device as well it is torch.device("cuda:0")

1

Traceback (most recent call last): File "example_copy.py", line 31, in lr_finder = LRFinder(model, optimizer, criterion) File "/home/snehaverma/anaconda3/envs/gmesh/lib/python3.6/site-packages/torch_lr_finder/lr_finder.py", line 166, in __init__ self.state_cacher.store("model", self.model.state_dict()) File "/home/snehaverma/anaconda3/envs/gmesh/lib/python3.6/site-packages/torch_lr_finder/lr_finder.py", line 624, in store self.cached.update({key:...

msverma101

Lr-finder with multiple inputs, outputs and losses

21

Hello, Firstly, thank you for this wonderful library. I have a model which expects 2 inputs. I am working with 2 kinds of images, one of size (512, 1536) and...

YashRunwal

ValueError ValDataLoaderIter next() call missing

1

In the _validate function, you try to iterate through the elements of ValDataLoaderIter with a simple for loop: https://github.com/davidtvs/pytorch-lr-finder/blob/acc5e7ee7711a460bf3e1cc5c5f05575ba1e1b4b/torch_lr_finder/lr_finder.py#L427 This throws a 'ValueError: too many values to unpack' because it...

paulhager

Question: Number of iterations

6

I tried the LR finder with 100 and with 1000 iterations (all other parameters staying the same) and got very different recommendations for the LR - for 100 iterations it...

swigicat

TrainDataLoadIter post-process network prediction

1

Hello. Currently the *DataLoadIter classes allow us to do some custom pre-processing of the (x, y) pairs with the "inputs_labels_from_batch" method. I have a network where I do some post-processing...

sevagh