You are mixing old/new Theano with old/new version of LeNet. If you use the
dev version of Theano,
make sure to update your LeNet example.

Some parameter name changes.

Make sure to use the dev version of Theano and the last version of LeNet.


On Wed, Nov 16, 2016 at 6:57 AM, Beatriz G. <[email protected]> wrote:

> Hi Everyone, I am trying to use strides (subsample) in LeNet example.
>
> So I have just changed:
>
>  # convolve input feature maps with filters
>         conv_out = conv2d(
>             input=input,
>             filters=self.W,
>             filter_shape=filter_shape,
>             input_shape=image_shape
>         )
>
>         # pool each feature map individually, using maxpooling
>         pooled_out = pool.pool_2d(
>             input=conv_out,
>             ds=poolsize,
>             ignore_border=True
>         )
>
>
>
> into:
>
>
>
> conv_out = conv.conv2d(
>     input=input,
>     filters=self.W,
>     subsample=(2,2),
>     filter_shape=filter_shape,
>     input_shape=image_shape
> )
>
> # downsample each feature map individually, using maxpooling
> pooled_out = pool.pool_2d(
>     input=conv_out,
>     ds=poolsize,
>     ignore_border=True,
>     mode='max'
> )
>
>
> And I am having the following error:
>
>
>
> Traceback (most recent call last):
> ... building the model
>   File "/home/beaa/Escritorio/Theano/Lenet_original/ejemploCNN_LeNet.py", 
> line 427, in <module>
>     evaluate_lenet5()
>   File "/home/beaa/Escritorio/Theano/Lenet_original/ejemploCNN_LeNet.py", 
> line 193, in evaluate_lenet5
>     poolsize=(2, 2)ut
>   File "/home/beaa/Escritorio/Theano/Lenet_original/ejemploCNN_LeNet.py", 
> line 105, in __init__
>     input_shape=image_shape
>   File 
> "/home/beaa/.local/lib/python2.7/site-packages/theano/tensor/nnet/conv.py", 
> line 151, in conv2d
>     imshp=imshp, kshp=kshp, nkern=nkern, bsize=bsize, **kargs)
> TypeError: __init__() got an unexpected keyword argument 'input_shape'
>
>
>
>
>
>
> Also, I would k¡like to know if the 'fanout' variable had to be changed,
> because the number of output neurons would not be the same, any ideas?
>
> Thanks for your help.
>
> Regards.
>
> --
>
> ---
> You received this message because you are subscribed to the Google Groups
> "theano-users" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to [email protected].
> For more options, visit https://groups.google.com/d/optout.
>

-- 

--- 
You received this message because you are subscribed to the Google Groups 
"theano-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
For more options, visit https://groups.google.com/d/optout.

Reply via email to