[theano-users] from DownsampleFactorMax to Pool in Theano 1.0.1

[Antonio95100]

Hi all,
I'm trying to train the VoxNet <https://github.com/dimatura/voxnet>3D/Volumetric
Convolutional Neural Networks, based on Theano+Lasagne.
Since I have installed Theano 1.01 and I don't want to downgrade to Theano
0.8.2, I modified the "max_pool_3d
<https://github.com/dimatura/voxnet/blob/master/voxnet/max_pool_3d.py>"
original code 'cause the *DownsampleFactorMax *module changed name in the
latest Theano version. So I replaced the following rows:

*op = T.signal.downsample.DownsampleFactorMax((ds[1], ds[2]),
ignore_border)*
*output = op(input_4D)*

with these:

*op = T.signal.pool.Pool(ignore_border)(input, ws=(ds[1],ds[2]))*
*output = op(input_4D)*

and I receive the following error message:


*File "/home//VoxNet/voxnet/voxnet/max_pool_3d.py", line 78, in max_pool_3d*
* output = op(input_4D)*
*TypeError: 'TensorVariable' object is not callable*

What is wrong in my update?
Thank you in advance for any suggestion.
Cheers.

[Pascal Lamblin]

/op = T.signal.downsample.DownsampleFactorMax((ds[1], ds[2]),
ignore_border)/
/output = op(input_4D)/
/op = T.signal.pool.Pool(ignore_border)(input, ws=(ds[1],ds[2]))/
/output = op(input_4D)/

The line-to-line equivalent would be:

op = T.signal.pool.Pool(ignore_border)
output = op(input_4D, ws=(ds[1], ds[2]))

/File "/home//VoxNet/voxnet/voxnet/max_pool_3d.py", line 78, in max_pool_3d/
/    output = op(input_4D)/
/TypeError: 'TensorVariable' object is not callable/
/
/
What is wrong in my update?
Thank you in advance for any suggestion.
Cheers.
--
---
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
For more options, visit https://groups.google.com/d/optout.

[Antonio95100]

Thank you very much, now it works.

Post by Antonio95100
Hi all,
I'm trying to train the VoxNet <https://github.com/dimatura/voxnet>3D/Volumetric
Convolutional Neural Networks, based on Theano+Lasagne.
Since I have installed Theano 1.01 and I don't want to downgrade to Theano
0.8.2, I modified the "max_pool_3d
<https://github.com/dimatura/voxnet/blob/master/voxnet/max_pool_3d.py>"
original code 'cause the *DownsampleFactorMax *module changed name in the
*op = T.signal.downsample.DownsampleFactorMax((ds[1], ds[2]),
ignore_border)*
*output = op(input_4D)*
*op = T.signal.pool.Pool(ignore_border)(input, ws=(ds[1],ds[2]))*
*output = op(input_4D)*
*File "/home//VoxNet/voxnet/voxnet/max_pool_3d.py", line 78, in max_pool_3d*
* output = op(input_4D)*
*TypeError: 'TensorVariable' object is not callable*
What is wrong in my update?
Thank you in advance for any suggestion.
Cheers.