Python cntk.parameter() Examples

The following are 30 code examples of cntk.parameter(). 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 cntk , or try the search function .
Example #1
Source File: cntk_backend.py    From keras-lambda with MIT License 6 votes vote down vote up 
def random_normal_variable(
        shape,
        mean,
        scale,
        dtype=_FLOATX,
        name=None,
        seed=None):
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e7)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    return C.parameter(
        shape=shape,
        init=C.initializer.normal(
            scale=scale,
            seed=seed),
        dtype=dtype,
        name=name)
Example #2
Source File: cntk_backend.py    From GraphicDesignPatternByPython with MIT License 6 votes vote down vote up 
def random_uniform_variable(shape, low, high,
                            dtype=None, name=None, seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e3)

    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    scale = (high - low) / 2
    p = C.parameter(
        shape,
        init=C.initializer.uniform(
            scale,
            seed=seed),
        dtype=dtype,
        name=name)
    return variable(value=p.value + low + scale)
Example #3
Source File: cntk_backend.py    From keras-lambda with MIT License 6 votes vote down vote up 
def random_uniform_variable(shape, low, high, dtype=_FLOATX,
                            name=None, seed=None):
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e3)

    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    scale = (high - low) / 2
    p = C.parameter(
        shape,
        init=C.initializer.uniform(
            scale,
            seed=seed),
        dtype=dtype,
        name=name)
    return variable(value=p.value + low + scale)
Example #4
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 6 votes vote down vote up 
def random_uniform_variable(shape, low, high,
                            dtype=None, name=None, seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e3)

    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    scale = (high - low) / 2
    p = C.parameter(
        shape,
        init=C.initializer.uniform(
            scale,
            seed=seed),
        dtype=dtype,
        name=name)
    return variable(value=p.value + low + scale)
Example #5
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 6 votes vote down vote up 
def random_uniform_variable(shape, low, high,
                            dtype=None, name=None, seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e3)

    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    scale = (high - low) / 2
    p = C.parameter(
        shape,
        init=C.initializer.uniform(
            scale,
            seed=seed),
        dtype=dtype,
        name=name)
    return variable(value=p.value + low + scale)
Example #6
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 6 votes vote down vote up 
def random_uniform_variable(shape, low, high,
                            dtype=None, name=None, seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e3)

    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    scale = (high - low) / 2
    p = C.parameter(
        shape,
        init=C.initializer.uniform(
            scale,
            seed=seed),
        dtype=dtype,
        name=name)
    return variable(value=p.value + low + scale)
Example #7
Source File: cntk_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up 
def random_uniform_variable(shape, low, high,
                            dtype=None, name=None, seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e3)

    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    scale = (high - low) / 2
    p = C.parameter(
        shape,
        init=C.initializer.uniform(
            scale,
            seed=seed),
        dtype=dtype,
        name=name)
    return variable(value=p.value + low + scale)
Example #8
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 6 votes vote down vote up 
def random_uniform_variable(shape, low, high,
                            dtype=None, name=None, seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e3)

    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    scale = (high - low) / 2
    p = C.parameter(
        shape,
        init=C.initializer.uniform(
            scale,
            seed=seed),
        dtype=dtype,
        name=name)
    return variable(value=p.value + low + scale)
Example #9
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 6 votes vote down vote up 
def random_uniform_variable(shape, low, high,
                            dtype=None, name=None, seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e3)

    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    scale = (high - low) / 2
    p = C.parameter(
        shape,
        init=C.initializer.uniform(
            scale,
            seed=seed),
        dtype=dtype,
        name=name)
    return variable(value=p.value + low + scale)
Example #10
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def truncated_normal(shape, mean=0.0, stddev=1.0, dtype=None, seed=None):
    if seed is None:
        seed = np.random.randint(1, 10e6)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    return C.parameter(
        shape, init=C.initializer.truncated_normal(
            stddev, seed=seed), dtype=dtype)
Example #11
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def random_normal_variable(
        shape,
        mean,
        scale,
        dtype=None,
        name=None,
        seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e7)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    return C.parameter(
        shape=shape,
        init=C.initializer.normal(
            scale=scale,
            seed=seed),
        dtype=dtype,
        name=name)
Example #12
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def truncated_normal(shape, mean=0.0, stddev=1.0, dtype=None, seed=None):
    if seed is None:
        seed = np.random.randint(1, 10e6)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    return C.parameter(
        shape, init=C.initializer.truncated_normal(
            stddev, seed=seed), dtype=dtype)
Example #13
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def random_normal_variable(
        shape,
        mean,
        scale,
        dtype=None,
        name=None,
        seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e7)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    return C.parameter(
        shape=shape,
        init=C.initializer.normal(
            scale=scale,
            seed=seed),
        dtype=dtype,
        name=name)
Example #14
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def random_normal_variable(
        shape,
        mean,
        scale,
        dtype=None,
        name=None,
        seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e7)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    return C.parameter(
        shape=shape,
        init=C.initializer.normal(
            scale=scale,
            seed=seed),
        dtype=dtype,
        name=name)
Example #15
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def truncated_normal(shape, mean=0.0, stddev=1.0, dtype=None, seed=None):
    if seed is None:
        seed = np.random.randint(1, 10e6)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    return C.parameter(
        shape, init=C.initializer.truncated_normal(
            stddev, seed=seed), dtype=dtype)
Example #16
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def random_normal_variable(
        shape,
        mean,
        scale,
        dtype=None,
        name=None,
        seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e7)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    return C.parameter(
        shape=shape,
        init=C.initializer.normal(
            scale=scale,
            seed=seed),
        dtype=dtype,
        name=name)
Example #17
Source File: logistic_regression.py    From ngraph-python with Apache License 2.0 5 votes vote down vote up 
def linear_layer(input_var, output_dim):
    input_dim = input_var.shape[0]

    weight_param = C.parameter(shape=(input_dim, output_dim))
    bias_param = C.parameter(shape=(output_dim))

    return C.times(input_var, weight_param) + bias_param
Example #18
Source File: cntk_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def random_normal_variable(
        shape,
        mean,
        scale,
        dtype=None,
        name=None,
        seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e7)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    return C.parameter(
        shape=shape,
        init=C.initializer.normal(
            scale=scale,
            seed=seed),
        dtype=dtype,
        name=name)
Example #19
Source File: cntk_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def truncated_normal(shape, mean=0.0, stddev=1.0, dtype=None, seed=None):
    if seed is None:
        seed = np.random.randint(1, 10e6)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    return C.parameter(
        shape, init=C.initializer.truncated_normal(
            stddev, seed=seed), dtype=dtype)
Example #20
Source File: cntk_backend.py    From keras-lambda with MIT License 5 votes vote down vote up 
def variable(value, dtype=_FLOATX, name=None):
    if name is None:
        name = ''

    if isinstance(
            value,
            C.variables.Constant) or isinstance(
            value,
            C.variables.Parameter):
        value = value.value

    # we don't support init parameter with symbolic op, so eval it first as
    # workaround
    if isinstance(value, C.cntk_py.Function):
        value = eval(value)

    shape = value.shape if hasattr(value, 'shape') else ()
    if hasattr(value, 'dtype') and value.dtype != dtype and len(shape) > 0:
        value = value.astype(dtype)
    # cntk will init type based on the value type
    v = C.parameter(shape=shape,
                    init=value,
                    name=_prepare_name(name, 'variable'))
    v._keras_shape = v.shape
    v._uses_learning_phase = False
    return v
Example #21
Source File: cntk_backend.py    From keras-lambda with MIT License 5 votes vote down vote up 
def truncated_normal(shape, mean=0.0, stddev=1.0, dtype=None, seed=None):
    if seed is None:
        seed = np.random.randint(1, 10e6)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    return C.parameter(
        shape, init=C.initializer.truncated_normal(
            stddev, seed=seed), dtype=dtype)
Example #22
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def truncated_normal(shape, mean=0.0, stddev=1.0, dtype=None, seed=None):
    if seed is None:
        seed = np.random.randint(1, 10e6)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    return C.parameter(
        shape, init=C.initializer.truncated_normal(
            stddev, seed=seed), dtype=dtype)
Example #23
Source File: feed_forward.py    From ngraph-python with Apache License 2.0 5 votes vote down vote up 
def linear_layer(input_var, output_dim):
    input_dim = input_var.shape[0]

    weight = C.parameter(shape=(input_dim, output_dim))
    bias = C.parameter(shape=(output_dim))

    return bias + C.times(input_var, weight)
Example #24
Source File: cntk_backend.py    From GraphicDesignPatternByPython with MIT License 5 votes vote down vote up 
def random_normal_variable(
        shape,
        mean,
        scale,
        dtype=None,
        name=None,
        seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e7)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    p = C.parameter(
        shape=shape,
        init=C.initializer.normal(
            scale=scale,
            seed=seed),
        dtype=dtype,
        name=name)
    return variable(value=p.value + mean)
Example #25
Source File: cntk_backend.py    From GraphicDesignPatternByPython with MIT License 5 votes vote down vote up 
def truncated_normal(shape, mean=0.0, stddev=1.0, dtype=None, seed=None):
    if seed is None:
        seed = np.random.randint(1, 10e6)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    return C.parameter(
        shape, init=C.initializer.truncated_normal(
            stddev, seed=seed), dtype=dtype)
Example #26
Source File: LayerUtils.py    From end2end_AU_speech with MIT License 5 votes vote down vote up 
def conv_from_weights(x, weights, bias=None, padding=True, name=""):
    """ weights is a numpy array """
    k = C.parameter(shape=weights.shape, init=weights)
    y = C.convolution(k, x, auto_padding=[False, padding, padding])
    if bias:
        b = C.parameter(shape=bias.shape, init=bias)
        y = y + bias
    y = C.alias(y, name=name)
    return y


# bi-directional recurrence function op
# fwd, bwd: a recurrent op, LSTM or GRU
Example #27
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def random_normal_variable(
        shape,
        mean,
        scale,
        dtype=None,
        name=None,
        seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e7)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    return C.parameter(
        shape=shape,
        init=C.initializer.normal(
            scale=scale,
            seed=seed),
        dtype=dtype,
        name=name)
Example #28
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def truncated_normal(shape, mean=0.0, stddev=1.0, dtype=None, seed=None):
    if seed is None:
        seed = np.random.randint(1, 10e6)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    return C.parameter(
        shape, init=C.initializer.truncated_normal(
            stddev, seed=seed), dtype=dtype)
Example #29
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def random_normal_variable(
        shape,
        mean,
        scale,
        dtype=None,
        name=None,
        seed=None):
    if dtype is None:
        dtype = floatx()
    if seed is None:
        # ensure that randomness is conditioned by the Numpy RNG
        seed = np.random.randint(10e7)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    if name is None:
        name = ''

    return C.parameter(
        shape=shape,
        init=C.initializer.normal(
            scale=scale,
            seed=seed),
        dtype=dtype,
        name=name)
Example #30
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def truncated_normal(shape, mean=0.0, stddev=1.0, dtype=None, seed=None):
    if seed is None:
        seed = np.random.randint(1, 10e6)
    if dtype is None:
        dtype = np.float32
    else:
        dtype = _convert_string_dtype(dtype)

    return C.parameter(
        shape, init=C.initializer.truncated_normal(
            stddev, seed=seed), dtype=dtype)