Python theano.tensor.all() Examples

The following are 30 code examples of theano.tensor.all(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module theano.tensor , or try the search function .
Example #1
Source File: test_elemwise.py    From attention-lvcsr with MIT License 6 votes vote down vote up
def test_c(self):
        if not theano.config.cxx:
            raise SkipTest("G++ not available, so we need to skip this test.")

        for dtype in ["floatX", "complex64", "complex128", "int8", "uint8"]:
            self.with_linker(gof.CLinker(), scalar.add, dtype=dtype)
            self.with_linker(gof.CLinker(), scalar.mul, dtype=dtype)
        for dtype in ["floatX", "int8", "uint8"]:
            self.with_linker(gof.CLinker(), scalar.minimum, dtype=dtype)
            self.with_linker(gof.CLinker(), scalar.maximum, dtype=dtype)
            self.with_linker(gof.CLinker(), scalar.and_, dtype=dtype,
                             tensor_op=tensor.all)
            self.with_linker(gof.CLinker(), scalar.or_, dtype=dtype,
                             tensor_op=tensor.any)
        for dtype in ["int8", "uint8"]:
            self.with_linker(gof.CLinker(), scalar.or_, dtype=dtype)
            self.with_linker(gof.CLinker(), scalar.and_, dtype=dtype)
            self.with_linker(gof.CLinker(), scalar.xor, dtype=dtype) 
Example #2
Source File: thutil.py    From Depth-Map-Prediction with GNU General Public License v3.0 6 votes vote down vote up
def local_gpu_togpu(node):
        if node.op == gpu_from_host:
            host_input = node.inputs[0]
            if host_input.owner and \
                    hasattr(host_input.owner.op, 'make_gpu_node'):
                try:
                    gpu_inputs = map(gpu_from_host, host_input.owner.inputs)
                except TypeError:
                    return False
                return [host_input.owner.op.make_gpu_node(*gpu_inputs)]
        elif hasattr(node.op, 'make_gpu_node') and \
                all([x.owner and x.owner.op == host_from_gpu
                     for x in node.inputs]):
            gpu_inputs = [x.owner.inputs[0] for x in node.inputs]
            return [host_from_gpu(node.op.make_gpu_node(*gpu_inputs))]
        return False 
Example #3
Source File: test_elemwise.py    From D-VAE with MIT License 6 votes vote down vote up
def test_c(self):
        if not theano.config.cxx:
            raise SkipTest("G++ not available, so we need to skip this test.")

        for dtype in ["floatX", "complex64", "complex128", "int8", "uint8"]:
            self.with_linker(gof.CLinker(), scalar.add, dtype=dtype)
            self.with_linker(gof.CLinker(), scalar.mul, dtype=dtype)
        for dtype in ["floatX", "int8", "uint8"]:
            self.with_linker(gof.CLinker(), scalar.minimum, dtype=dtype)
            self.with_linker(gof.CLinker(), scalar.maximum, dtype=dtype)
            self.with_linker(gof.CLinker(), scalar.and_, dtype=dtype,
                             tensor_op=tensor.all)
            self.with_linker(gof.CLinker(), scalar.or_, dtype=dtype,
                             tensor_op=tensor.any)
        for dtype in ["int8", "uint8"]:
            self.with_linker(gof.CLinker(), scalar.or_, dtype=dtype)
            self.with_linker(gof.CLinker(), scalar.and_, dtype=dtype)
            self.with_linker(gof.CLinker(), scalar.xor, dtype=dtype) 
Example #4
Source File: attention.py    From attention-lvcsr with MIT License 6 votes vote down vote up
def compute_weights(self, energies, attended_mask):
        if self.energy_normalizer == 'softmax':
            logger.debug("Using softmax attention weights normalization")
            energies = energies - energies.max(axis=0)
            unnormalized_weights = tensor.exp(energies)
        elif self.energy_normalizer == 'logistic':
            logger.debug("Using smoothfocus (logistic sigm) "
                        "attention weights normalization")
            unnormalized_weights = tensor.nnet.sigmoid(energies)
        elif self.energy_normalizer == 'relu':
            logger.debug("Using ReLU attention weights normalization")
            unnormalized_weights = tensor.maximum(energies/1000., 0.0)
        else:
            raise Exception("Unknown energey_normalizer: {}"
                            .format(self.energy_computer))
        if attended_mask:
            unnormalized_weights *= attended_mask

        # If mask consists of all zeros use 1 as the normalization coefficient
        normalization = (unnormalized_weights.sum(axis=0) +
                         tensor.all(1 - attended_mask, axis=0))
        return unnormalized_weights / normalization 
Example #5
Source File: theano_backend.py    From keras-lambda with MIT License 5 votes vote down vote up
def zeros(shape, dtype=None, name=None):
    """Instantiates an all-zeros variable.
    """
    if dtype is None:
        dtype = floatx()
    return variable(np.zeros(shape), dtype, name) 
Example #6
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def all(x, axis=None, keepdims=False):
    """Bitwise reduction (logical AND).
    """
    return T.all(x, axis=axis, keepdims=keepdims) 
Example #7
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def _preprocess_conv2d_kernel(kernel, data_format):
    # As of Keras 2.0.0, all kernels are normalized
    # on the format `(rows, cols, input_depth, depth)`,
    # independently of `data_format`.
    # Theano expects `(depth, input_depth, rows, cols)`.
    kernel = kernel.dimshuffle((3, 2, 0, 1))
    return kernel 
Example #8
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def zeros(shape, dtype=None, name=None):
    """Instantiates an all-zeros variable.
    """
    if dtype is None:
        dtype = floatx()
    return variable(np.zeros(shape), dtype, name) 
Example #9
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def ones(shape, dtype=None, name=None):
    """Instantiates an all-ones variable.
    """
    if dtype is None:
        dtype = floatx()
    return variable(np.ones(shape), dtype, name) 
Example #10
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def all(x, axis=None, keepdims=False):
    """Bitwise reduction (logical AND).
    """
    return T.all(x, axis=axis, keepdims=keepdims) 
Example #11
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def ones(shape, dtype=None, name=None):
    """Instantiates an all-ones variable.
    """
    if dtype is None:
        dtype = floatx()
    return variable(np.ones(shape), dtype, name) 
Example #12
Source File: theano_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up
def _preprocess_conv2d_kernel(kernel, data_format):
    # As of Keras 2.0.0, all kernels are normalized
    # on the format `(rows, cols, input_depth, depth)`,
    # independently of `data_format`.
    # Theano expects `(depth, input_depth, rows, cols)`.
    kernel = kernel.dimshuffle((3, 2, 0, 1))
    return kernel 
Example #13
Source File: theano_backend.py    From KerasNeuralFingerprint with MIT License 5 votes vote down vote up
def zeros(shape, dtype=_FLOATX, name=None):
    '''Instantiate an all-zeros variable.
    '''
    return variable(np.zeros(shape), dtype, name) 
Example #14
Source File: theano_backend.py    From KerasNeuralFingerprint with MIT License 5 votes vote down vote up
def ones(shape, dtype=_FLOATX, name=None):
    '''Instantiate an all-ones variable.
    '''
    return variable(np.ones(shape), dtype, name) 
Example #15
Source File: theano_backend.py    From KerasNeuralFingerprint with MIT License 5 votes vote down vote up
def all(x, axis=None, keepdims=False):
    '''Bitwise reduction (logical AND).
    '''
    return T.all(x, axis=axis, keepdims=keepdims) 
Example #16
Source File: theano_backend.py    From keras-lambda with MIT License 5 votes vote down vote up
def all(x, axis=None, keepdims=False):
    """Bitwise reduction (logical AND).
    """
    return T.all(x, axis=axis, keepdims=keepdims) 
Example #17
Source File: theano_backend.py    From keras-lambda with MIT License 5 votes vote down vote up
def _preprocess_conv3d_kernel(kernel, data_format):
    # As of Keras 2.0.0, all kernels are normalized
    # on the format `(space, input_depth, depth)`,
    # independently of `data_format`.
    # Theano expects `(depth, input_depth, space)`.
    kernel = kernel.dimshuffle((4, 3, 0, 1, 2))
    return kernel 
Example #18
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def all(x, axis=None, keepdims=False):
    """Bitwise reduction (logical AND).
    """
    return T.all(x, axis=axis, keepdims=keepdims) 
Example #19
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def zeros(shape, dtype=None, name=None):
    """Instantiates an all-zeros variable.
    """
    if dtype is None:
        dtype = floatx()
    return variable(np.zeros(shape), dtype, name) 
Example #20
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def _preprocess_conv3d_kernel(kernel, data_format):
    # As of Keras 2.0.0, all kernels are normalized
    # on the format `(space, input_depth, depth)`,
    # independently of `data_format`.
    # Theano expects `(depth, input_depth, space)`.
    kernel = kernel.dimshuffle((4, 3, 0, 1, 2))
    return kernel 
Example #21
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def all(x, axis=None, keepdims=False):
    """Bitwise reduction (logical AND).
    """
    return T.all(x, axis=axis, keepdims=keepdims) 
Example #22
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def ones(shape, dtype=None, name=None):
    """Instantiates an all-ones variable.
    """
    if dtype is None:
        dtype = floatx()
    return variable(np.ones(shape), dtype, name) 
Example #23
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def zeros(shape, dtype=None, name=None):
    """Instantiates an all-zeros variable.
    """
    if dtype is None:
        dtype = floatx()
    return variable(np.zeros(shape), dtype, name) 
Example #24
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def _preprocess_conv3d_kernel(kernel, data_format):
    # As of Keras 2.0.0, all kernels are normalized
    # on the format `(space, input_depth, depth)`,
    # independently of `data_format`.
    # Theano expects `(depth, input_depth, space)`.
    kernel = kernel.dimshuffle((4, 3, 0, 1, 2))
    return kernel 
Example #25
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def _preprocess_conv2d_kernel(kernel, data_format):
    # As of Keras 2.0.0, all kernels are normalized
    # on the format `(rows, cols, input_depth, depth)`,
    # independently of `data_format`.
    # Theano expects `(depth, input_depth, rows, cols)`.
    kernel = kernel.dimshuffle((3, 2, 0, 1))
    return kernel 
Example #26
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def ones(shape, dtype=None, name=None):
    """Instantiates an all-ones variable.
    """
    if dtype is None:
        dtype = floatx()
    return variable(np.ones(shape), dtype, name) 
Example #27
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def zeros(shape, dtype=None, name=None):
    """Instantiates an all-zeros variable.
    """
    if dtype is None:
        dtype = floatx()
    return variable(np.zeros(shape), dtype, name) 
Example #28
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def _preprocess_conv3d_kernel(kernel, data_format):
    # As of Keras 2.0.0, all kernels are normalized
    # on the format `(space, input_depth, depth)`,
    # independently of `data_format`.
    # Theano expects `(depth, input_depth, space)`.
    kernel = kernel.dimshuffle((4, 3, 0, 1, 2))
    return kernel 
Example #29
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def _preprocess_conv2d_kernel(kernel, data_format):
    # As of Keras 2.0.0, all kernels are normalized
    # on the format `(rows, cols, input_depth, depth)`,
    # independently of `data_format`.
    # Theano expects `(depth, input_depth, rows, cols)`.
    kernel = kernel.dimshuffle((3, 2, 0, 1))
    return kernel 
Example #30
Source File: theano_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up
def _preprocess_conv2d_kernel(kernel, data_format):
    # As of Keras 2.0.0, all kernels are normalized
    # on the format `(rows, cols, input_depth, depth)`,
    # independently of `data_format`.
    # Theano expects `(depth, input_depth, rows, cols)`.
    kernel = kernel.dimshuffle((3, 2, 0, 1))
    return kernel