Discussions
following error I have got
from opendeep.models.container import Prototype
Traceback (most recent call last):
File "", line 1, in
File "opendeep/init.py", line 29, in
from . import models
File "opendeep/models/init.py", line 3, in
from .model import *
File "opendeep/models/model.py", line 13, in
from theano.compat.python2x import OrderedDict # use this compatibility OrderedDict
ImportError: No module named python2x
Theano error when running Quick example
When running the Quick example of the MLP on the MNIST data I am getting the following error when running on Python 3.5:
Failed to connect to Bokeh
I trying to run the "Monitors and Live Plotting" tutorial, but when i run the code a HTTP 599 error is returned with the IOError "Cannot push session document because we failed to connect to the server (to start the server, try the 'bokeh serve' command)". The server is running and listen to localhost:5006. At the same time, the server says "INFO:tornado.general:Malformed HTTP message from 127.0.0.1: Malformed HTTP request line".
Plotting loss function in Jupyter
Is there a way to plot the loss function as a function of iteration number (during training) within the Jupyter notebook?
AttributeError: 'Plot' object has no attribute 'channels'
I am new to OpenDeep, trying out the example code for monitoring channels, copy and pasted the code from the example page, but shows this error : Plot object has no attribute 'channel'. Can anyone please help. Thanks
A binary classifier experiment
Hi,
Fantastic Library, so clear!
I was just wondering, i am trying to use the library for a binary classifier experiment using the log loss function to train the model. This is for a university experiment around benchmarking different models. Would you have some time to provide an example of how to use the library to achieve the above goal.
Many thanks,
Best,
Andrew
Get output vector before the softmax layer ?
Dear all,
I would like to know how to get the probabilities (output values of the neural network) of each class of a given trained MLP in OpenDeep ?
This would play the role of a confidence.
Thanks a lot !
how to predict after traing
Hi
I have a question
After training a model , How can I predict using sample data ?
Setup
I'm looking to evaluate OpenDeep. Any recommendations on GPU hardware (NVidia graphics cards) and what Distribution of Linux to use?
when i run rnnrbm_mnist.py test program I got this error
INFO:opendeep.optimization.optimizer:Train monitors: {'crossentropy/train': 0.45665097, 'error/train': 0.17261043}
Traceback (most recent call last):
File "/home/elliotnam/workspace2/facerecognition/rnnrbm_mnist.py", line 95, in
run_sequence(1)
File "/home/elliotnam/workspace2/facerecognition/rnnrbm_mnist.py", line 54, in run_sequence
optimizer.train(plot=plot)
File "/usr/local/lib/python2.7/dist-packages/opendeep-0.0.9a0-py2.7.egg/opendeep/optimization/optimizer.py", line 391, in train
self.STOP = self._perform_one_epoch(train_function, plot)
File "/usr/local/lib/python2.7/dist-packages/opendeep-0.0.9a0-py2.7.egg/opendeep/optimization/optimizer.py", line 464, in _perform_one_epoch
plot.update_plots(epoch=self.epoch_counter, monitors=current_mean_monitors)
File "/usr/local/lib/python2.7/dist-packages/opendeep-0.0.9a0-py2.7.egg/opendeep/monitor/plot.py", line 213, in update_plots
line_color=self.colors[color_idx % len(self.colors)])
File "/home/elliotnam/.local/lib/python2.7/site-packages/bokeh/_glyph_functions.py", line 37, in func
glyph = _make_glyph(glyphclass, kwargs, glyph_ca)
File "/home/elliotnam/.local/lib/python2.7/site-packages/bokeh/plotting_helpers.py", line 144, in _make_glyph
return glyphclass(kws)
File "/home/elliotnam/.local/lib/python2.7/site-packages/bokeh/plot_object.py", line 90, in init
super(PlotObject, self).init(kwargs)
File "/home/elliotnam/.local/lib/python2.7/site-packages/bokeh/properties.py", line 357, in init
setattr(self, name, value)
File "/home/elliotnam/.local/lib/python2.7/site-packages/bokeh/properties.py", line 371, in setattr
(name, self.class.name, text, nice_join(matches)))
AttributeError: unexpected attribute 'y_axis_label' to Line, possible attributes are line_alpha, line_cap, line_color, line_dash, line_dash_offset, line_join, line_width, name, session, tags, visible, x or y