keras_lr_finder
keras_lr_finder copied to clipboard
surmenok
Plots the change of the loss function of a Keras model when the learning rate is exponentially increasing.
I am using the latest version of tensorflow and keras and while running LRfinder class i got an error as shown below --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in...
I have looked into the post "Estimating an Optimal Learning Rate For a Deep Neural Network", it suggested to use training loss to determine the best learning rate to use...
Hi! I'm having troubles figuring out whether my model is not working correctly or I'm using wrong parameters for LRFinder. Here's my model summary. It's a fully convolutional network for...
In LRFinder.find() and LRFinder.find_generator(), there is a call to the following functions: ``` self.model.save_weights('tmp.h5') self.model.load_weights('tmp.h5') ``` This is unsafe: In the case where several python processes running LRFinder in parallel,...
After reading this blog post: https://sgugger.github.io/how-do-you-find-a-good-learning-rate.html It seems that you can get better smoothing by using an exponential weighting. Could this potentially provide better a learning rate? I'll make a...
How to use [get_best_lr](https://github.com/surmenok/keras_lr_finder/blob/f1013c997080792259478a25908c80c08a2f2fbd/keras_lr_finder/lr_finder.py#L145) method from the class [LRFinder](https://github.com/surmenok/keras_lr_finder/blob/f1013c997080792259478a25908c80c08a2f2fbd/keras_lr_finder/lr_finder.py#L8) I tried ``` lr_finder.get_best_lr(sma=20) ``` I got the following error. ``` --------------------------------------------------------------------------- IndexError Traceback (most recent call last) in ----> 1...
Hi, Thank you for providing this awesome library. I gave it a try to my CNN model and it did not work well. Is this only works for Feed Forward...
When using `find_generator`: https://github.com/surmenok/keras_lr_finder/blob/7870043d86101010b2a644df22b4018af58534fb/keras_lr_finder/lr_finder.py#L76 `lr_mult` causes the learning rate to converge at `end_lr` after only 1 epoch. If you want to use 2 or more epochs, then your learning rate...
Code to replicate the error: ``` # 1. Import callbacks from keras.models import Sequential from keras.layers import Flatten, Dense, Conv2D, MaxPooling2D from keras.callbacks import ModelCheckpoint from keras.datasets import mnist !pip...
