itdxer / neupy Goto Github PK
View Code? Open in Web Editor NEWNeuPy is a Tensorflow based python library for prototyping and building neural networks
Home Page: http://neupy.com
License: MIT License
NeuPy is a Tensorflow based python library for prototyping and building neural networks
Home Page: http://neupy.com
License: MIT License
Possible solution
def train(self, input_data):
input_data = format_data(input_data)
Implement transform
and fit_transfom
in BaseSkeleton
class
I am using oja's rule on dataset of size 400x156300. It seems to crash my RAM. I am not sure what is causing this. Please help.
I have 12 GB of RAM.
Tried using memmap still crash!!
[num_sample,num_feat]=train_data.shape
filename = path.join(mkdtemp(), 'train_data.dat')
memmap_train = np.memmap(filename, dtype='float32', mode='w+', shape=(num_sample,num_feat))
memmap_train[:] = train_data[:]
del train_data,test_data
ojanet = algorithms.Oja(minimized_data_size=1250,step=1e-10,verbose=True,show_epoch=1)
ojanet.train(memmap_train, epsilon=1e-3,epochs=10000)
red_train_data = ojanet.predict(memmap_train)
ojanet.plot_errors(logx=False)
pdb.set_trace()
Related to module neupy.core.properties
Also there should be possibility to initialize custom error function
theano.gof.fg.MissingInputError: ("An input of the graph, used to compute Elemwise{sub,no_inplace}(<TensorType(float64, scalar)>, <TensorType(float64, scalar)>), was not provided and not given a value.Use the Theano flag exception_verbosity='high',for more information on this error.", <TensorType(float64, scalar)>)
Now only works diagonal displacement.
Hide legend if there is no negative values in the input matrix
Add tests to verify that all the algorithms work with pandas data frames and fix the ones that don't work
There also must be available option that disable this possibility
Define __repr__
method for the memory based networks
Possible use case
from neupy.datasets import load_discrete_digits
digits = load_discrete_digits()
By default for a case when number of epochs is greater or equal to 10
I am trying to find some license information about the project into official site and this repository, but can not. According to this link https://pypi.python.org/pypi/neupy/0.1.1 this project have MIT License.
Can you add LICENSE
file to the repository, please?
Should be active only when it update as an attribute in initialisation step.
Possible problems: Zero division singular matrix
Possible use case
dhnet = algorithms.DiscreteHopfieldNetwork(mode='sync')
dhnet.train(data)
dhnet.energy(otherdata)
In addition there are would be good to have exception for step modification optimization classes
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.