Python theano.tensor.as_tensor() Examples

def make_node(self, frames, n, axis):
        """
        Compute an n-point fft of frames along given axis.

        """
        _frames = tensor.as_tensor(frames, ndim=2)
        _n = tensor.as_tensor(n, ndim=0)
        _axis = tensor.as_tensor(axis, ndim=0)
        if self.half and _frames.type.dtype.startswith('complex'):
            raise TypeError('Argument to HalfFFT must not be complex', frames)
        spectrogram = tensor.zmatrix()
        buf = generic()
        # The `buf` output is present for future work
        # when we call FFTW directly and re-use the 'plan' that FFTW creates.
        # In that case, buf would store a CObject encapsulating the plan.
        rval = Apply(self, [_frames, _n, _axis], [spectrogram, buf])
        return rval 

def make_node(self, frames, n, axis):
        """
        Compute an n-point fft of frames along given axis.

        """
        _frames = tensor.as_tensor(frames, ndim=2)
        _n = tensor.as_tensor(n, ndim=0)
        _axis = tensor.as_tensor(axis, ndim=0)
        if self.half and _frames.type.dtype.startswith('complex'):
            raise TypeError('Argument to HalfFFT must not be complex', frames)
        spectrogram = tensor.zmatrix()
        buf = generic()
        # The `buf` output is present for future work
        # when we call FFTW directly and re-use the 'plan' that FFTW creates.
        # In that case, buf would store a CObject encapsulating the plan.
        rval = Apply(self, [_frames, _n, _axis], [spectrogram, buf])
        return rval 

def get_aggregator(self):
        initialized = shared_like(0.)
        expression_acc = shared_like(self.expression)

        # Dummy default expression to use as the previously-accumulated
        # value, that has the same shape as the new result
        expression_zeros = tensor.as_tensor(self.expression).zeros_like()

        conditional_update_expr = self.expression + ifelse(initialized,
                                                           expression_acc,
                                                           expression_zeros)

        initialization_updates = [(expression_acc,
                                   tensor.zeros_like(expression_acc)),
                                  (initialized, 0.)]
        accumulation_updates = [(expression_acc,
                                 conditional_update_expr),
                                (initialized, 1.)]
        aggregator = Aggregator(aggregation_scheme=self,
                                initialization_updates=initialization_updates,
                                accumulation_updates=accumulation_updates,
                                readout_variable=(expression_acc))
        return aggregator 

def set_rest_ref_matrix(self, number_of_points_per_surface):
        ref_positions = T.cumsum(T.concatenate((T.stack([0]), number_of_points_per_surface[:-1] + 1)))
        cum_rep = T.cumsum(T.concatenate((T.stack([0]), number_of_points_per_surface)))

        ref_points_init = T.zeros((cum_rep[-1], 3))
        ref_points_loop, update_ = theano.scan(self.repeat_list,
                                               outputs_info=[ref_points_init],
                                               sequences=[self.surface_points_all[ref_positions],
                                                          dict(input=cum_rep, taps=[0, 1])],
                                               non_sequences=[T.as_tensor(3)],

                                               return_list=False)

        #   ref_points_loop = theano.printing.Print('loop')(ref_points_loop)
        ref_points = ref_points_loop[-1]
        #  ref_points = T.repeat(self.surface_points_all[ref_positions], number_of_points_per_surface, axis=0)

        rest_mask = T.ones(T.stack([self.surface_points_all.shape[0]]), dtype='int16')
        rest_mask = T.set_subtensor(rest_mask[ref_positions], 0)
        rest_mask = T.nonzero(rest_mask)[0]
        rest_points = self.surface_points_all[rest_mask]
        return [ref_points, rest_points, ref_positions, rest_mask] 

def set_nugget_surface_points(self, ref_positions, rest_mask, number_of_points_per_surface):
        # ref_nugget = T.repeat(self.nugget_effect_scalar_T[ref_positions], number_of_points_per_surface)
        cum_rep = T.cumsum(T.concatenate((T.stack([0]), number_of_points_per_surface)))
        ref_nugget_init = T.zeros((cum_rep[-1], 1))
        ref_nugget_loop, update_ = theano.scan(self.repeat_list,
                                               outputs_info=[ref_nugget_init],
                                               sequences=[self.nugget_effect_scalar_T[ref_positions],
                                                          dict(input=cum_rep, taps=[0, 1])],
                                               non_sequences=[T.as_tensor(1)],
                                               return_list=False)

        # ref_nugget_loop = theano.printing.Print('loop')(ref_nugget_loop)
        ref_nugget = ref_nugget_loop[-1]

        rest_nugget = self.nugget_effect_scalar_T[rest_mask]
        nugget_rest_ref = ref_nugget.reshape((1, -1))[0] + rest_nugget
        return nugget_rest_ref 

def get_aggregator(self):
        initialized = shared_like(0.)
        numerator_acc = shared_like(self.numerator)
        denominator_acc = shared_like(self.denominator)

        # Dummy default expression to use as the previously-accumulated
        # value, that has the same shape as the new result
        numerator_zeros = tensor.as_tensor(self.numerator).zeros_like()
        denominator_zeros = tensor.as_tensor(self.denominator).zeros_like()

        conditional_update_num = self.numerator + ifelse(initialized,
                                                         numerator_acc,
                                                         numerator_zeros)
        conditional_update_den = self.denominator + ifelse(initialized,
                                                           denominator_acc,
                                                           denominator_zeros)

        initialization_updates = [(numerator_acc,
                                   tensor.zeros_like(numerator_acc)),
                                  (denominator_acc,
                                   tensor.zeros_like(denominator_acc)),
                                  (initialized, 0.)]
        accumulation_updates = [(numerator_acc,
                                 conditional_update_num),
                                (denominator_acc,
                                 conditional_update_den),
                                (initialized, 1.)]
        aggregator = Aggregator(aggregation_scheme=self,
                                initialization_updates=initialization_updates,
                                accumulation_updates=accumulation_updates,
                                readout_variable=(numerator_acc /
                                                  denominator_acc))
        return aggregator 

def infer_shape(self, node, shapes):
        return [shapes[0] + (tt.as_tensor(self.N),)] 

def infer_shape(self, node, shapes):
        return [
            shapes[0] + (tt.as_tensor(self.N),),
            shapes[0] + (tt.as_tensor(self.N),),
            shapes[0] + (tt.as_tensor(self.N),),
        ] 

def infer_shape(self, node, shapes):
        return [
            shapes[0] + (tt.as_tensor(self.N),),
            shapes[0] + (tt.as_tensor(self.N),),
            shapes[0] + (tt.as_tensor(self.N),),
            shapes[0] + (tt.as_tensor(self.N),),
            shapes[0] + (tt.as_tensor(self.N),),
            shapes[0] + (tt.as_tensor(self.N),),
        ] 

def max_pool(images, imgshp, maxpoolshp):
    """Implements a max pooling layer

    Takes as input a 2D tensor of shape batch_size x img_size and
    performs max pooling.  Max pooling downsamples by taking the max
    value in a given area, here defined by maxpoolshp. Outputs a 2D
    tensor of shape batch_size x output_size.

    :param images: 2D tensor containing images on which to apply convolution.
                   Assumed to be of shape batch_size x img_size
    :param imgshp: tuple containing image dimensions
    :param maxpoolshp: tuple containing shape of area to max pool over

    :return: out1, symbolic result (2D tensor)
    :return: out2, logical shape of the output
    """
    N = numpy
    poolsize = N.int64(N.prod(maxpoolshp))

    # imgshp contains either 2 entries (height,width) or 3 (nfeatures,h,w)
    # in the first case, default nfeatures to 1
    if N.size(imgshp) == 2:
        imgshp = (1,) + imgshp

    # construct indices and index pointers for sparse matrix, which,
    # when multiplied with input images will generate a stack of image
    # patches
    indices, indptr, spmat_shape, sptype, outshp = \
            convolution_indices.conv_eval(imgshp, maxpoolshp,
                                          maxpoolshp, mode='valid')

#    print 'XXXXXXXXXXXXXXXX MAX POOLING LAYER XXXXXXXXXXXXXXXXXXXX'
#    print 'imgshp = ', imgshp
#    print 'maxpoolshp = ', maxpoolshp
#    print 'outshp = ', outshp

    # build sparse matrix, then generate stack of image patches
    csc = theano.sparse.CSM(sptype)(N.ones(indices.size), indices,
                                    indptr, spmat_shape)
    patches = sparse.structured_dot(csc, images.T).T

    pshape = tensor.stack([images.shape[0] *\
                               tensor.as_tensor(N.prod(outshp)),
                           tensor.as_tensor(imgshp[0]),
                           tensor.as_tensor(poolsize)])
    patch_stack = tensor.reshape(patches, pshape, ndim=3)

    out1 = tensor.max(patch_stack, axis=2)

    pshape = tensor.stack([images.shape[0],
                           tensor.as_tensor(N.prod(outshp)),
                           tensor.as_tensor(imgshp[0])])
    out2 = tensor.reshape(out1, pshape, ndim=3)

    out3 = tensor.DimShuffle(out2.broadcastable, (0, 2, 1))(out2)

    return tensor.flatten(out3, 2), outshp 

def max_pool(images, imgshp, maxpoolshp):
    """Implements a max pooling layer

    Takes as input a 2D tensor of shape batch_size x img_size and
    performs max pooling.  Max pooling downsamples by taking the max
    value in a given area, here defined by maxpoolshp. Outputs a 2D
    tensor of shape batch_size x output_size.

    :param images: 2D tensor containing images on which to apply convolution.
                   Assumed to be of shape batch_size x img_size
    :param imgshp: tuple containing image dimensions
    :param maxpoolshp: tuple containing shape of area to max pool over

    :return: out1, symbolic result (2D tensor)
    :return: out2, logical shape of the output
    """
    N = numpy
    poolsize = N.int64(N.prod(maxpoolshp))

    # imgshp contains either 2 entries (height,width) or 3 (nfeatures,h,w)
    # in the first case, default nfeatures to 1
    if N.size(imgshp) == 2:
        imgshp = (1,) + imgshp

    # construct indices and index pointers for sparse matrix, which,
    # when multiplied with input images will generate a stack of image
    # patches
    indices, indptr, spmat_shape, sptype, outshp = \
            convolution_indices.conv_eval(imgshp, maxpoolshp,
                                          maxpoolshp, mode='valid')

#    print 'XXXXXXXXXXXXXXXX MAX POOLING LAYER XXXXXXXXXXXXXXXXXXXX'
#    print 'imgshp = ', imgshp
#    print 'maxpoolshp = ', maxpoolshp
#    print 'outshp = ', outshp

    # build sparse matrix, then generate stack of image patches
    csc = theano.sparse.CSM(sptype)(N.ones(indices.size), indices,
                                    indptr, spmat_shape)
    patches = sparse.structured_dot(csc, images.T).T

    pshape = tensor.stack([images.shape[0] *\
                               tensor.as_tensor(N.prod(outshp)),
                           tensor.as_tensor(imgshp[0]),
                           tensor.as_tensor(poolsize)])
    patch_stack = tensor.reshape(patches, pshape, ndim=3)

    out1 = tensor.max(patch_stack, axis=2)

    pshape = tensor.stack([images.shape[0],
                           tensor.as_tensor(N.prod(outshp)),
                           tensor.as_tensor(imgshp[0])])
    out2 = tensor.reshape(out1, pshape, ndim=3)

    out3 = tensor.DimShuffle(out2.broadcastable, (0, 2, 1))(out2)

    return tensor.flatten(out3, 2), outshp 

def __init__(self, rng, inputVar, cfgParams, copyLayer=None, layerNum=None):
        """
        Allocate a PoolLayer with shared variable internal parameters.

        :type rng: numpy.random.RandomState
        :param rng: a random number generator used to initialize weights

        :type inputVar: theano.tensor.dtensor4
        :param inputVar: symbolic image tensor, of shape image_shape

        :type cfgParams: PoolLayerParams
        """

        floatX = theano.config.floatX  # @UndefinedVariable

        outputDim = cfgParams.outputDim
        poolsize = cfgParams.poolsize
        inputDim = cfgParams.inputDim
        activation = cfgParams.activation
        poolType = cfgParams.poolType

        self.cfgParams = cfgParams
        self.layerNum = layerNum

        self.inputVar = inputVar

        if inputVar.type.ndim != 4:
            raise TypeError()

        self.params = []
        self.weights = []

        # downsample each feature map individually, using maxpooling
        if poolType == 0:
            # use maxpooling
            pooled_out = pool_2d(input=self.inputVar, ds=poolsize, ignore_border=True)
        elif poolType == 1:
            # use average pooling
            pooled_out = theano.sandbox.neighbours.images2neibs(ten4=self.inputVar, neib_shape=poolsize, mode='ignore_borders').mean(axis=-1)
            new_shape = T.cast(T.join(0, self.inputVar.shape[:-2], T.as_tensor([self.inputVar.shape[2]//poolsize[0]]), T.as_tensor([self.inputVar.shape[3]//poolsize[1]])), 'int64')
            pooled_out = T.reshape(pooled_out, new_shape, ndim=4)
        elif poolType == 3:
            # use subsampling and ignore border
            pooled_out = self.inputVar[:, :, :(inputDim[2]//poolsize[0])*poolsize[0], :(inputDim[3]//poolsize[1])*poolsize[1]][:, :, ::poolsize[0], ::poolsize[1]]
        elif poolType == -1:
            # no pooling at all
            pooled_out = self.inputVar
        else:
            raise ValueError("Unknown pool type!")

        self.output = (pooled_out if activation is None
                       else activation(pooled_out))

        self.output.name = 'output_layer_{}'.format(self.layerNum) 

def updates(self, gradients):
        """
        Return symbolic updates to apply given a set of gradients
        on the parameters being optimized.

        Parameters
        ----------
        gradients : list of tensor_likes
            List of symbolic gradients for the parameters contained
            in self.params, in the same order as in self.params.

        Returns
        -------
        updates : dict
            A dictionary with the shared variables in self.params as keys
            and a symbolic expression of how they are to be updated each
            SGD step as values.

        Notes
        -----
        `cost_updates` is a convenient helper function that takes all
        necessary gradients with respect to a given symbolic cost.
        """
        ups = {}
        # Add the learning rate/iteration updates
        l_ups, learn_rates = self.learning_rate_updates(gradients)
        safe_update(ups, l_ups)

        # Get the updates from sgd_updates, a PyLearn library function.
        p_up = dict(self.sgd_updates(self.params, gradients, learn_rates))

        # Add the things in p_up to ups
        safe_update(ups, p_up)

        # Clip the values if needed.
        # We do not want the clipping values to force an upcast
        # of the update: updates should have the same type as params
        for param, (p_min, p_max) in six.iteritems(self.clipping_values):
            p_min = tensor.as_tensor(p_min)
            p_max = tensor.as_tensor(p_max)
            dtype = param.dtype
            if p_min.dtype != dtype:
                p_min = tensor.cast(p_min, dtype)
            if p_max.dtype != dtype:
                p_max = tensor.cast(p_max, dtype)
            ups[param] = tensor.clip(ups[param], p_min, p_max)

        # Return the updates dictionary.
        return ups