getting the error message

[Ori226]

Hi!
Great post about auto encoder!
I had this issue when trying to run the code in ipython note book:
(BTW, I'm pretty new to python and libraries you used so the error might be a result of fault installation)

c:\anaconda\lib\lasagne-master\lasagne\init.py:86: UserWarning: The uniform initializer no longer uses Glorot et al.'s approach to determine the bounds, but defaults to the range (-0.01, 0.01) instead. Please use the new GlorotUniform initializer to get the old behavior. GlorotUniform is now the default for all layers.
warnings.warn("The uniform initializer no longer uses Glorot et al.'s "

---

TypeError Traceback (most recent call last)
in ()
39 verbose=1,
40 )
---> 41 ae.fit(X_train, X_out)

C:\Anaconda\lib\site-packages\nolearn\lasagne.pyc in fit(self, X, y)
136 out = getattr(self, '_output_layer', None)
137 if out is None:
--> 138 out = self._output_layer = self.initialize_layers()
139 if self.verbose:
140 self._print_layer_info(self.get_all_layers())

C:\Anaconda\lib\site-packages\nolearn\lasagne.pyc in initialize_layers(self, layers)
367 for (layer_name, layer_factory) in self.layers[1:]:
368 layer_params = self._get_params_for(layer_name)
--> 369 layer = layer_factory(layer, **layer_params)
370
371 self._output_layer = layer

TypeError: init() takes at least 3 arguments (2 given)

[mikesj-public]

Heya, sorry I don't have a lot of time to help, but I think the issue is probably with the version of lasagne you are using, they changed the parameters you have to give to some of the layers. I would suggest that you try building the layers outside of the nolearn call so like

lasagne.layers.Conv2DLayer(**params you want to hand in from nolearn)

and for the other layers as well until you figure out which layer is giving the bug. Otherwise I will try and update the code this weekend!

[Ori226]

Thanks for your help, I'll try it!

On Wed, May 20, 2015 at 7:53 PM, mikesj-public notifications@github.com
wrote:

Heya, sorry I don't have a lot of time to help, but I think the issue is
probably with the version of lasagne you are using, they changed the
parameters you have to give to some of the layers.

I would suggest that you try building the layers outside of the nolearn
call so like

lasagne.layers.Conv2DLayer(**params you want to hand in from nolearn)

and for the other layers as well until you figure out which layer is
giving the bug.

Otherwise I will try and update the code this weekend!

—
Reply to this email directly or view it on GitHub
#2 (comment)
.

[Tgaaly]

Any help with this? Seems like this code is too old for lasagne. Is there an easy fix?

I got the following error:

Using gpu device 0: GeForce GTX TITAN X (CNMeM is disabled)
Traceback (most recent call last):
  File "mnist_conv_autoencode.py", line 158, in <module>
    ae.fit(X_train, X_out)
  File "/home/tarek/Libraries/anaconda/lib/python2.7/site-packages/nolearn/lasagne/base.py", line 445, in fit
    self.initialize()
  File "/home/tarek/Libraries/anaconda/lib/python2.7/site-packages/nolearn/lasagne/base.py", line 286, in initialize
    out = self._output_layer = self.initialize_layers()
  File "/home/tarek/Libraries/anaconda/lib/python2.7/site-packages/nolearn/lasagne/base.py", line 383, in initialize_layers
    chain_exception(TypeError(msg), e)
  File "/home/tarek/Libraries/anaconda/lib/python2.7/site-packages/nolearn/_compat.py", line 14, in chain_exception
    exec("raise exc1, None, sys.exc_info()[2]")
  File "/home/tarek/Libraries/anaconda/lib/python2.7/site-packages/nolearn/lasagne/base.py", line 378, in initialize_layers
    layer = layer_factory(**layer_kw)
  File "/home/tarek/Libraries/anaconda/lib/python2.7/site-packages/lasagne/layers/conv.py", line 391, in __init__
    super(Conv2DLayer, self).__init__(incoming, **kwargs)
TypeError: Failed to instantiate <class 'lasagne.layers.conv.Conv2DLayer'> with args {'incoming': <lasagne.layers.input.InputLayer object at 0x7fd404989a10>, 'name': 'conv', 'nonlinearity': None, 'filter_size': (7, 7), 'num_filters': 32, 'border_mode': 'valid'}.
Maybe parameter names have changed?

[mikesj-public]

Heya, someone has updated to latest version of lasagne, you can view and/or install version numbers for theano/nolearn/lasagne from requirements.txt

Let me know if there are any problems.

[appu0507]

Did it work with the latest version I am still getting the same error as above ?

[yshean]

I encountered this issue and removing the 'border_mode' parameter from model did the trick.

[xmuszq]

Hi yshean,

Could you give more details about how you resolve it?

[yinchuandong]

@yshean Your solution works. @xmuszq you can refer to http://lasagne.readthedocs.org/en/latest/modules/layers/conv.html#lasagne.layers.Conv2DLayer, Here gives the parameters of Conv2DLayer. Some parameters have been updated.

[wtlim]

@yshean It works fine.
Is it a difference between lasagne v0.1 and v0.2dev1??