cyberzhg / keras-adabound Goto Github PK
View Code? Open in Web Editor NEWAdaBound optimizer in Keras
Home Page: https://pypi.org/project/keras-adabound/
License: MIT License
AdaBound optimizer in Keras
Home Page: https://pypi.org/project/keras-adabound/
License: MIT License
Describe the Bug
A clear and concise description of what the bug is.
Hi, I wanted to try this interesting optimizer but I got this error using te example code.
Does the package don't support categorical_crossentropy?
Thanks!
Version Info
Minimal Codes To Reproduce
from keras_adabound import AdaBound
autoencoder.compile(loss="categorical_crossentropy", optimizer=AdaBound(lr=0.001, final_lr=0.1), metrics=['categorical_accuracy'])
######error output###
File "C:\chap\GazeTracking\synthetic\train_segNot3D.py", line 389, in <module>
autoencoder.compile(loss="categorical_crossentropy", optimizer=AdaBound(lr=0.001, final_lr=0.1), metrics=['categorical_accuracy'])
File "C:\ProgramData\Anaconda3\envs\crash\lib\site-packages\keras_adabound\optimizers.py", line 31, in __init__
self.lr = K.variable(lr, name='lr')
AttributeError: can't set attribute
pass
I just wanted to notify that without the base LR scaling done at this line https://github.com/Luolc/AdaBound/blob/master/adabound/adabound.py#L110, your optimizer will not properly lower the bounds when LR decay is applied, either via LearningRateSchedule or ReduceLROnPlateau callbacks.
Describe the Bug
I am working on Google Colab
Error:
AttributeError Traceback (most recent call last)
in ()
1 from keras_adabound import AdaBound
----> 2 model.compile(optimizer=AdaBound(lr=1e-3, final_lr=0.1), loss='binary_crossentropy')
/usr/local/lib/python3.6/dist-packages/keras_adabound/optimizers.py in init(self, lr, final_lr, base_lr, beta_1, beta_2, gamma, epsilon, decay, weight_decay, amsgrad, **kwargs)
29 with K.name_scope(self.class.name):
30 self.iterations = K.variable(0, dtype='int64', name='iterations')
---> 31 self.lr = K.variable(lr, name='lr')
32 self.final_lr = K.variable(final_lr, name='final_lr')
33 self.beta_1 = K.variable(beta_1, name='beta_1')
AttributeError: can't set attribute
Version Info
I'm using the latest version
Minimal Codes To Reproduce
!pip install keras-adabound
from keras_adabound import AdaBound
model.compile(optimizer=AdaBound(lr=1e-3, final_lr=0.1), loss='binary_crossentropy')
pass
Describe the Bug
A clear and concise description of what the bug is.
Version Info
Minimal Codes To Reproduce
import keras_bert
pass
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.