benanne

import theano
import theano.tensor as T
import numpy as np

def local_feature_extractor(x, W, b, shape_info=None):
    xr = x.dimshuffle(0, 2, 'x', 1) # in: (num_examples, num_input_features, 1, num_timesteps)
    Wr = W.dimshuffle(0, 1, 'x', 2) # filters: (num_output_features, num_input_features, 1, width)

    # the output of the convolution should be equal in length to the input
    len_left = (Wr.shape[3] - 1) / 2

benanne

s = set()

with open("kaggle_visible_evaluation_triplets.txt", 'r') as f:
    for line in f:
        user, _, _ = line.strip().split('\t')
        s.add(user)
        
print "%d users" % len(s)

benanne

[ 96%] Building NVCC (Device) object extra/cuda/lib/THC/CMakeFiles/THC.dir//./THC_generated_THC.cu.o
/usr/lib/gcc/x86_64-unknown-linux-gnu/4.7.0/../../../../include/c++/4.7.0/ext/atomicity.h(48): error: identifier "__atomic_fetch_add" is undefined

/usr/lib/gcc/x86_64-unknown-linux-gnu/4.7.0/../../../../include/c++/4.7.0/ext/atomicity.h(52): error: identifier "__atomic_fetch_add" is undefined

/usr/lib/gcc/x86_64-unknown-linux-gnu/4.7.0/../../../../include/c++/4.7.0/limits(1405): error: identifier "__int128" is undefined

/usr/lib/gcc/x86_64-unknown-linux-gnu/4.7.0/../../../../include/c++/4.7.0/limits(1409): error: identifier "__int128" is undefined

/usr/lib/gcc/x86_64-unknown-linux-gnu/4.7.0/../../../../include/c++/4.7.0/limits(1412): error: identifier "__int128" is undefined

benanne

import numpy as np


def freq2mel(freq):
    return 1127.01048 * np.log(1 + freq / 700.0)

def mel2freq(mel):
    return (np.exp(mel / 1127.01048) - 1) * 700

def mel_binning_matrix(specgram_window_size, sample_frequency, num_mel_bands):

benanne

import threading
import Queue
import time

def buffered_gen(source_gen, buffer_size=2, sleep_time=1):
    """
    Generator that runs a slow source generator in a separate thread.
    buffer_size: the maximal number of items to pre-generate (length of the buffer)
    """
    buffer = Queue.Queue(maxsize=buffer_size)

benanne

import time
import multiprocessing as mp

def buffered_gen_mp(source_gen, buffer_size=2, sleep_time=1):
    """
    Generator that runs a slow source generator in a separate process.
    buffer_size: the maximal number of items to pre-generate (length of the buffer)
    """
    buffer = mp.Queue(maxsize=buffer_size)

benanne

import theano
import theano.tensor as T
from theano.tensor.opt import register_canonicalize

class ConsiderConstant(theano.compile.ViewOp):
    def grad(self, args, g_outs):
        return [T.zeros_like(g_out) for g_out in g_outs]

consider_constant = ConsiderConstant()
register_canonicalize(theano.gof.OpRemove(consider_constant), name='remove_consider_constant')

benanne

import numpy as np 
import theano

import theano.misc.pycuda_init
import theano.sandbox.cuda as cuda
from theano.misc.pycuda_utils import to_gpuarray, to_cudandarray

from scikits.cuda import fft

benanne

"""This tutorial introduces the LeNet5 neural network architecture
using Theano.  LeNet5 is a convolutional neural network, good for
classifying images. This tutorial shows how to build the architecture,
and comes with all the hyper-parameters you need to reproduce the
paper's MNIST results.


This implementation simplifies the model in the following ways:

 - LeNetConvPool doesn't implement location-specific gain and bias parameters

benanne

* GeForce GTX 780Ti "Superclocked"
* drivers 340.24
* CUDA 6.0


sander@sander-precision:~/tmp/schluter/Theano$ for x in full valid subsample grads; do cuda-memcheck nosetests theano/sandbox/cuda/tests/test_conv_cuda_ndarray.py:test_gemm_$x; done
========= CUDA-MEMCHECK
Using gpu device 0: GeForce GTX 780 Ti
========= Invalid __global__ read of size 4
=========     at 0x000000e0 in sgemm_sm_heavy_nt_ldg