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

Hi all, I'm trying to train the 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

[theano-users] Compilation issue in Theano 1.0.1

Hi, I have a windows machine and the content of the .theanorc file is: [global] floatX = float32 device = cpu [nvcc] fastmath = True flags = -LC:\Temp\Anaconda3\libs compiler_bindir = "C:\Temp\Anaconda3\Library\mingw-w64\bin" [blas] ldflags = -LC:\Temp\Anaconda3\Library\bin -lmkl_rt [cuda] ro

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

On 2018-05-03 04:12 AM, Antonio95100 wrote: /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)/ The line-to-line equivalent would be: op =

Re: [theano-users] Compilation issue in Theano 1.0.1

If you add "nocleanup=True" to the config options (for instance in the .theanorc), can you see more things in Model_1\compiledir...? I see a backslash before "Model_1" in the config option, is that intended, or an artifact of the email? Is it necessary? What happens if you put the whole path i

Re: [theano-users] Compilation issue in Theano 1.0.1

Thanks Pascal for the prompt reply. To answer your questions: A) Added the option nocleanup=True to the .theanorc file B) The backslash before "Model 1". In my previous attempts in Theano 0.9.0, this was the way that I found to make it work. Following your suggestion, I edited the header of t

[theano-users] Using theano.tensor.repeat with repeats.ndim == 1

An example of what I am doing: Here m is an fmatrix, and v is an ivector out = T.repeat(m, v, axis=0) The forward pass works fine, but there is no gradient code implemented. This works fine when both inputs are vectors but not as above. I am not familiar with theano enough to fill in the mis

Re: [theano-users] Compilation issue in Theano 1.0.1

On 2018-05-03 02:00 PM, ivan.d.marroq...@gmail.com wrote:> A) Added the option nocleanup=True to the .theanorc file Thanks. This makes sure the "mod.c" file you mention later is not deleted. B) The backslash before "Model 1". In my previous attempts in Theano 0.9.0, this was the way that I fou

Re: [theano-users] Using theano.tensor.repeat with repeats.ndim == 1

Does it work with two matrices? If so, you can try to use dimshuffle to make v a "row" instead of a "vector". On 2018-05-03 03:24 PM, Kristjan Arumae wrote: An example of what I am doing: Here m is an fmatrix, and v is an ivector out = T.repeat(m, v, axis=0) The forward pass works fine, but

Re: [theano-users] Compilation issue in Theano 1.0.1

Thanks for the suggestion. I checked the disk space and have ~700Gbytes. Then, I tested with "base_compiledir" using the entire path. This time, a sub-folder with this name was created: UsersIMarroquinDocumentsMy_Python_ScriptsMLPSEG_contestIndependent_ScriptsModel_1 Because the name is way

Re: [theano-users] Using theano.tensor.repeat with repeats.ndim == 1

No, it only works with two vectors. 2 Matrixes is not supported in numpy either I don't think, since it is likely to mess up the output shape. On Thursday, May 3, 2018 at 4:03:15 PM UTC-4, Pascal Lamblin wrote: > > Does it work with two matrices? > If so, you can try to use dimshuffle to make v

Re: [theano-users] Compilation issue in Theano 1.0.1

On 2018-05-03 04:50 PM, ivan.d.marroq...@gmail.com wrote: Thanks for the suggestion. I checked the disk space and have ~700Gbytes. Then, I tested with "base_compiledir" using the entire path. This time,  a sub-folder with this name was created: UsersIMarroquinDocumentsMy_Python_ScriptsMLPSEG

Re: [theano-users] Using theano.tensor.repeat with repeats.ndim == 1

Oh, right. Then, I don't think it will be implemented. And I don't think RepeatOp is optimized to use the GPU anyway. Sorry about that On 2018-05-03 06:01 PM, Kristjan Arumae wrote: No, it only works with two vectors.  2 Matrixes is not supported in numpy either I don't think, since it is lik

Re: [theano-users] Compilation issue in Theano 1.0.1

Also, according to this [1], it may be your antivirus preventing the creation of the file. [1] https://stackoverflow.com/questions/7655471/ld-exe-cannot-open-output-file-permission-denied On 2018-05-03 06:32 PM, Pascal Lamblin wrote: On 2018-05-03 04:50 PM, ivan.d.marroq...@gmail.com wrote: