def get_dim(self, name):
     if name == 'input_':
         return self.input_dim
     if name == 'output':
         return tuple(DownsampleFactorMax.out_shape(self.input_dim,
                                                    self.pooling_size,
                                                    st=self.step))

    def test_DownsampleFactorMaxGrad_grad_st_extra(self):
        """checks the gradient of the gradient for the case that
        stride is used for extra examples"""
        rng = numpy.random.RandomState(utt.fetch_seed())
        maxpoolshps = ((5, 3), (5, 3), (5, 3), (5, 5), (3, 2), (7, 7), (9, 9))
        stridesizes = ((3, 2), (7, 5), (10, 6), (1, 1), (2, 3), (10, 10), (1, 1))
        imvsizs = ((16, 16), (16, 16), (16, 16), (8, 5), (8, 5), (8, 5), (8, 5))

        for indx in numpy.arange(len(maxpoolshps)):
            imvsize = imvsizs[indx]
            imval = rng.rand(1, 2, imvsize[0], imvsize[1])
            stride = stridesizes[indx]
            maxpoolshp = maxpoolshps[indx]
            for ignore_border in [True, False]:
                grad_shape = DownsampleFactorMax.out_shape(
                    imval.shape, maxpoolshp, ignore_border=ignore_border, st=stride
                )
                grad_val = rng.rand(*grad_shape)

                def mp(input, grad):
                    out = DownsampleFactorMax(maxpoolshp, ignore_border=ignore_border, st=stride)(input)
                    grad_op = DownsampleFactorMaxGrad(maxpoolshp, ignore_border=ignore_border, st=stride)
                    return grad_op(input, out, grad)

                # skip the grad verification when the output is empty
                if numpy.prod(grad_shape) == 0:
                    continue
                utt.verify_grad(mp, [imval, grad_val], rng=rng)

    def test_AveragePoolPaddingStride_grad_grad(self):
        rng = numpy.random.RandomState(utt.fetch_seed())
        imgsizes = ((10, 10), (10, 5), (5, 5))
        avgpoolsizes = ((5, 3), (3, 5), (3, 3))
        stridesizes = ((3, 2), (2, 3), (3, 3))
        paddingsizes = ((2, 2), (2, 1), (2, 2))

        for i in range(len(imgsizes)):
            imgsize = imgsizes[i]
            imval = rng.rand(1, 1, imgsize[0], imgsize[1]) * 10.0
            avgpoolsize = avgpoolsizes[i]
            stridesize = stridesizes[i]
            paddingsize = paddingsizes[i]

            # 'average_exc_pad' with non-zero padding is not implemented
            for mode in ['sum', 'average_inc_pad']:
                grad_shape = DownsampleFactorMax.out_shape(imval.shape,
                                                           avgpoolsize, st=stridesize,
                                                           ignore_border=True, padding=paddingsize)
                grad_val = rng.rand(*grad_shape) * 10.0

                def mp(input, grad):
                    grad_op = AveragePoolGrad(avgpoolsize, ignore_border=True,
                                              st=stridesize, padding=paddingsize,
                                              mode=mode)
                    return grad_op(input, grad)
                utt.verify_grad(mp, [imval, grad_val], rng=rng)

    def test_DownsampleFactorMaxGrad_grad_st(self):
        """checks the gradient of the gradient for
        the case that stride is used"""
        rng = numpy.random.RandomState(utt.fetch_seed())
        maxpoolshps = ((1, 1), (3, 3), (5, 3))
        stridesizes = ((1, 1), (3, 3), (5, 7))
        imval = rng.rand(1, 2, 16, 16)

        for maxpoolshp in maxpoolshps:
            for ignore_border in [True, False]:
                for stride in stridesizes:
                    grad_shape = DownsampleFactorMax.out_shape(
                        imval.shape, maxpoolshp,
                        ignore_border=ignore_border, st=stride)
                    grad_val = rng.rand(*grad_shape)

                    def mp(input, grad):
                        out = DownsampleFactorMax(
                            maxpoolshp, ignore_border=ignore_border,
                            st=stride)(input)
                        grad_op = MaxPoolGrad(
                            maxpoolshp, ignore_border=ignore_border,
                            st=stride)
                        return grad_op(input, out, grad)

                    utt.verify_grad(mp, [imval, grad_val], rng=rng)

 def get_dim(self, name):
     if name == 'input_':
         return self.input_dim
     if name == 'output':
         return tuple(DownsampleFactorMax.out_shape(
             self.input_dim, self.pooling_size, st=self.step,
             ignore_border=self.ignore_border, padding=self.padding))

    def test_DownsampleFactorMaxPaddingStride_grad_grad(self):
        rng = numpy.random.RandomState(utt.fetch_seed())
        imgsizes = ((10, 10), (10, 5), (5, 5))
        maxpoolsizes = ((5, 3), (3, 5), (3, 3))
        stridesizes = ((3, 2), (2, 3), (3, 3))
        paddingsizes = ((2, 2), (2, 1), (2, 2))

        for i in range(len(imgsizes)):
            imgsize = imgsizes[i]
            imval = rng.rand(1, 1, imgsize[0], imgsize[1]) * 10.0
            maxpoolsize = maxpoolsizes[i]
            stridesize = stridesizes[i]
            paddingsize = paddingsizes[i]

            grad_shape = DownsampleFactorMax.out_shape(imval.shape,
                                                       maxpoolsize, st=stridesize,
                                                       ignore_border=True,
                                                       padding=paddingsize)
            grad_val = rng.rand(*grad_shape) * 10.0

            def mp(input, grad):
                out = DownsampleFactorMax(
                    maxpoolsize, ignore_border=True,
                    st=stridesize,
                    padding=paddingsize,
                    )(input)
                grad_op = MaxPoolGrad(maxpoolsize, ignore_border=True,
                                      st=stridesize, padding=paddingsize)
                return grad_op(input, out, grad)
            utt.verify_grad(mp, [imval, grad_val], rng=rng)

def pool_output_shape_2d(input_shape,
                         axes,
                         pool_shape,
                         strides,
                         pads,
                         ignore_border=True):
    """
    compute output shape for a pool
    """
    return tuple(DownsampleFactorMax.out_shape(
        imgshape=input_shape,
        ds=pool_shape,
        st=strides,
        ignore_border=ignore_border,
        padding=pads,
    ))

    def test_DownsampleFactorMaxGrad_grad(self):
        rng = numpy.random.RandomState(utt.fetch_seed())
        maxpoolshps = ((1, 1), (3, 2), (2, 3))
        imval = rng.rand(2, 3, 3, 4) * 10.0
        # more variance means numeric gradient will be more accurate

        for maxpoolshp in maxpoolshps:
            for ignore_border in [True, False]:
                # print 'maxpoolshp =', maxpoolshp
                # print 'ignore_border =', ignore_border
                # The shape of the gradient will be the shape of the output
                grad_shape = DownsampleFactorMax.out_shape(imval.shape, maxpoolshp, ignore_border=ignore_border)
                grad_val = rng.rand(*grad_shape) * 10.0

                def mp(input, grad):
                    out = DownsampleFactorMax(maxpoolshp, ignore_border=ignore_border)(input)
                    grad_op = DownsampleFactorMaxGrad(maxpoolshp, ignore_border=ignore_border)
                    return grad_op(input, out, grad)

                utt.verify_grad(mp, [imval, grad_val], rng=rng)

    def test_AveragePoolGrad_grad(self):
        rng = numpy.random.RandomState(utt.fetch_seed())
        avgpoolshps = ((1, 1), (3, 2), (2, 3))
        imval = rng.rand(2, 3, 3, 4) * 10.0
        # more variance means numeric gradient will be more accurate

        for avgpoolshp in avgpoolshps:
            for ignore_border in [True, False]:
                for mode in ['sum', 'average_inc_pad', 'average_exc_pad']:
                    # print 'maxpoolshp =', maxpoolshp
                    # print 'ignore_border =', ignore_border
                    # The shape of the gradient will be the shape of the output
                    grad_shape = DownsampleFactorMax.out_shape(
                        imval.shape, avgpoolshp, ignore_border=ignore_border)
                    grad_val = rng.rand(*grad_shape) * 10.0

                    def mp(input, grad):
                        grad_op = AveragePoolGrad(
                            avgpoolshp, ignore_border=ignore_border, mode=mode)
                        return grad_op(input, grad)

                    utt.verify_grad(mp, [imval, grad_val], rng=rng)

    def test_AveragePoolGrad_grad_st(self):
        """checks the gradient of the gradient for
        the case that stride is used"""
        rng = numpy.random.RandomState(utt.fetch_seed())
        avgpoolshps = ((1, 1), (3, 3), (5, 3))
        stridesizes = ((1, 1), (3, 3), (5, 7))
        imval = rng.rand(1, 2, 16, 16)

        for avgpoolshp in avgpoolshps:
            for ignore_border in [True, False]:
                for mode in ['sum', 'average_inc_pad', 'average_exc_pad']:
                    for stride in stridesizes:
                        grad_shape = DownsampleFactorMax.out_shape(
                            imval.shape, avgpoolshp,
                            ignore_border=ignore_border, st=stride)
                        grad_val = rng.rand(*grad_shape)

                        def mp(input, grad):
                            grad_op = AveragePoolGrad(
                                avgpoolshp, ignore_border=ignore_border,
                                st=stride, mode=mode)
                            return grad_op(input, grad)

                        utt.verify_grad(mp, [imval, grad_val], rng=rng)

    def test_DownsampleFactorMax(self):
        rng = numpy.random.RandomState(utt.fetch_seed())
        # generate random images
        maxpoolshps = ((1, 1), (2, 2), (3, 3), (2, 3))
        imval = rng.rand(4, 2, 16, 16)
        images = tensor.dtensor4()
        for maxpoolshp, ignore_border, mode in product(maxpoolshps,
                                                       [True, False],
                                                       ['max',
                                                        'sum',
                                                        'average_inc_pad',
                                                        'average_exc_pad']):
                # print 'maxpoolshp =', maxpoolshp
                # print 'ignore_border =', ignore_border

                # Pure Numpy computation
                numpy_output_val = self.numpy_max_pool_2d(imval, maxpoolshp,
                                                          ignore_border,
                                                          mode=mode)
                output = max_pool_2d(images, maxpoolshp, ignore_border,
                                     mode=mode)
                f = function([images, ], [output, ])
                output_val = f(imval)
                utt.assert_allclose(output_val, numpy_output_val)

                # DownsampleFactorMax op
                maxpool_op = DownsampleFactorMax(maxpoolshp,
                                                 ignore_border=ignore_border,
                                                 mode=mode)(images)

                output_shape = DownsampleFactorMax.out_shape(imval.shape, maxpoolshp,
                                                        ignore_border=ignore_border)
                utt.assert_allclose(numpy.asarray(output_shape), numpy_output_val.shape)
                f = function([images], maxpool_op)
                output_val = f(imval)
                utt.assert_allclose(output_val, numpy_output_val)

def maxpool_2d(z, in_dim, poolsize, poolstride):
    z = max_pool_2d(z, ds=poolsize, st=poolstride)
    output_size = tuple(DownsampleFactorMax.out_shape(in_dim, poolsize,
                                                      st=poolstride))
    return z, output_size

def init_net(num_of_classes, input_len, conv_params):
    """
    Major initialize of the neural net is in this method. You can adjust convolutional window size for each layer,
    number of filters for each layer and all the cascade parameters for every layer. We also initialize and define weights
    for neural net.
    :param num_of_classes: number of classes
    :param input_len: read (sequence chunk) length
    :return: weights in param variable, X and Y matrices, cost function, update function and maxima prediction
    """
    cwin1=4*6  # multiples of 4 because of data representation
    cwin2=3
    cwin3=2

    num_filters_1=32 / 2  # how many different filters to learn at each layer
    num_filters_2=48 / 2
    num_filters_3=64 / 2
    # size of convolution windows, for each layer different values can be used
    w = init_weights((num_filters_1, 1, 1, cwin1)) # first convolution, 32 filters, stack size 1, 1 rows, cwin1 columns
    w2 = init_weights((num_filters_2, num_filters_1, 1, cwin2)) # second convolution, 64 filters, stack size 32 (one stack for each filter from previous layer), 1 row, cwin2 columns
    w3 = init_weights((num_filters_3, num_filters_2, 1, cwin3)) # third convolution, 128 filters, stack size 64 (one stack for each filter from previous layes), 1 row, cwin3 columns

    print "#### CONVOLUTION PARAMETERS ####"
    print "cwin1 %d" % cwin1
    print "cwin2 %d" % cwin2
    print "cwin3 %d" % cwin3
    print "num_filters_1 %d" % num_filters_1
    print "num_filters_2 %d" % num_filters_2
    print "num_filters_3 %d" % num_filters_3

    # convolution: filters are moved by one position at a time, see parameter subsample=(1, 1)
    #
    # max pooling:
    #   scaling the input before applying the maxpool filter and
    #   displacement (stride) when sliding the max pool filters

    # l1 conv:
    es = input_len
    es = (es - cwin1 + 1)
    es = es / conv1_stride
    # l1 max_pool:
    es = DownsampleFactorMax.out_shape((1, es), (1, downscale1), st=(1, stride1))[1] # downscale for first layer
    print "l1 es:", es

    # l2 conv:
    es = (es - cwin2 + 1)
    # l2 max_pool:
    es = DownsampleFactorMax.out_shape((1, es), (1, downscale2), st=(1, stride2))[1] # downscale for second layer
    print "l2 es:", es

    # l3 conv:
    es = (es - cwin3 + 1)
    # l3 max_pool:
    es = DownsampleFactorMax.out_shape((1, es), (1, downscale3), st=(1, stride3))[1] # downscale for third layer
    print "l3 es:", es

    # downscaling is performed so that we correctly set number of filters in last layer

    w4 = init_weights((num_filters_3 * es, 500))  # fully conected last layer, connects the outputs of 128 filters to 500 (arbitrary) hidden nodes, which are then connected to the output nodes
    w_o = init_weights((500, num_of_classes))  # number of exptected classes

    # matrix types
    X = T.ftensor4()
    Y = T.fmatrix()

    noise_l1, noise_l2, noise_l3, noise_l4, noise_py_x = model(X, w, w2, w3, w4, 0.2, 0.5, w_o, conv_params)
    l1, l2, l3, l4, py_x = model(X, w, w2, w3, w4, 0., 0., w_o, conv_params)
    y_x = T.argmax(py_x, axis=1)  # maxima predictions

    cost = T.mean(T.nnet.categorical_crossentropy(noise_py_x, Y)) # classification matrix to optimize - maximize the value that is actually there and minimize the others
    params = [w, w2, w3, w4, w_o]
    updates = RMSprop(cost, params, lr=0.001) # update function

    return params, X, Y, cost, updates, y_x