Python cntk.times() Examples

The following are 30 code examples of cntk.times(). 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 DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def batch_dot(x, y, axes=None):
    x_shape = int_shape(x)
    y_shape = int_shape(y)

    if isinstance(axes, int):
        axes = (axes, axes)
    if axes is None:
        # behaves like tf.batch_matmul as default
        axes = [len(x_shape) - 1, len(y_shape) - 2]

    if len(x_shape) == 2 and len(y_shape) == 2:
        return sum(x * y, axis=1, keepdims=True)
    else:
        if len(y_shape) == 2:
            y = expand_dims(y)

        normalized_axis = []
        normalized_axis.append(_normalize_axis(axes[0], x)[0])
        normalized_axis.append(_normalize_axis(axes[1], y)[0])
        # transpose
        i = normalized_axis[0]
        while i < len(x.shape) - 1:
            x = C.swapaxes(x, i, i + 1)
            i += 1
        i = normalized_axis[1]
        while i > 0:
            y = C.swapaxes(y, i, i - 1)
            i -= 1
        result = C.times(x, y, output_rank=(len(y.shape) - 1)
                         if len(y.shape) > 1 else 1)
        if len(y_shape) == 2:
            result = squeeze(result, -1)
        return result
Example #2
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def dot(x, y):
    if len(x.shape) > 2 or len(y.shape) > 2:
        y_shape = int_shape(y)
        if len(y_shape) > 2:
            permutation = [len(y_shape) - 2]
            permutation += list(range(len(y_shape) - 2))
            permutation += [len(y_shape) - 1]
            y = C.transpose(y, perm=permutation)
        return C.times(x, y, len(y_shape) - 1)
    else:
        return C.times(x, y)
Example #3
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def batch_dot(x, y, axes=None):
    x_shape = int_shape(x)
    y_shape = int_shape(y)

    if isinstance(axes, int):
        axes = (axes, axes)
    if axes is None:
        # behaves like tf.batch_matmul as default
        axes = [len(x_shape) - 1, len(y_shape) - 2]

    if len(x_shape) == 2 and len(y_shape) == 2:
        return sum(x * y, axis=1, keepdims=True)
    else:
        if len(y_shape) == 2:
            y = expand_dims(y)

        normalized_axis = []
        normalized_axis.append(_normalize_axis(axes[0], x)[0])
        normalized_axis.append(_normalize_axis(axes[1], y)[0])
        # transpose
        i = normalized_axis[0]
        while i < len(x.shape) - 1:
            x = C.swapaxes(x, i, i + 1)
            i += 1
        i = normalized_axis[1]
        while i > 0:
            y = C.swapaxes(y, i, i - 1)
            i -= 1
        result = C.times(x, y, output_rank=(len(y.shape) - 1)
                         if len(y.shape) > 1 else 1)
        if len(y_shape) == 2:
            result = squeeze(result, -1)
        return result
Example #4
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def dot(x, y):
    if len(x.shape) > 2 or len(y.shape) > 2:
        y_shape = int_shape(y)
        if len(y_shape) > 2:
            permutation = [len(y_shape) - 2]
            permutation += list(range(len(y_shape) - 2))
            permutation += [len(y_shape) - 1]
            y = C.transpose(y, perm=permutation)
        return C.times(x, y, len(y_shape) - 1)
    else:
        return C.times(x, y)
Example #5
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def batch_dot(x, y, axes=None):
    x_shape = int_shape(x)
    y_shape = int_shape(y)

    if isinstance(axes, int):
        axes = (axes, axes)
    if axes is None:
        # behaves like tf.batch_matmul as default
        axes = [len(x_shape) - 1, len(y_shape) - 2]

    if len(x_shape) == 2 and len(y_shape) == 2:
        return sum(x * y, axis=1, keepdims=True)
    else:
        if len(y_shape) == 2:
            y = expand_dims(y)

        normalized_axis = []
        normalized_axis.append(_normalize_axis(axes[0], x)[0])
        normalized_axis.append(_normalize_axis(axes[1], y)[0])
        # transpose
        i = normalized_axis[0]
        while i < len(x.shape) - 1:
            x = C.swapaxes(x, i, i + 1)
            i += 1
        i = normalized_axis[1]
        while i > 0:
            y = C.swapaxes(y, i, i - 1)
            i -= 1
        result = C.times(x, y, output_rank=(len(y.shape) - 1)
                         if len(y.shape) > 1 else 1)
        if len(y_shape) == 2:
            result = squeeze(result, -1)
        return result
Example #6
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def gather(reference, indices):
    # There is a bug in cntk gather op which may cause crash.
    # We have made a fix but not catched in CNTK 2.1 release.
    # Will update with gather op in next release
    if _get_cntk_version() >= 2.2:
        return C.ops.gather(reference, indices)
    else:
        num_classes = reference.shape[0]
        one_hot_matrix = C.ops.one_hot(indices, num_classes)
        return C.times(one_hot_matrix, reference, output_rank=len(reference.shape) - 1)
Example #7
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def dot(x, y):
    if len(x.shape) > 2 or len(y.shape) > 2:
        y_shape = int_shape(y)
        if len(y_shape) > 2:
            permutation = [len(y_shape) - 2]
            permutation += list(range(len(y_shape) - 2))
            permutation += [len(y_shape) - 1]
            y = C.transpose(y, perm=permutation)
        return C.times(x, y, len(y_shape) - 1)
    else:
        return C.times(x, y)
Example #8
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def batch_dot(x, y, axes=None):
    x_shape = int_shape(x)
    y_shape = int_shape(y)

    if isinstance(axes, int):
        axes = (axes, axes)
    if axes is None:
        # behaves like tf.batch_matmul as default
        axes = [len(x_shape) - 1, len(y_shape) - 2]

    if len(x_shape) == 2 and len(y_shape) == 2:
        return sum(x * y, axis=1, keepdims=True)
    else:
        if len(y_shape) == 2:
            y = expand_dims(y)

        normalized_axis = []
        normalized_axis.append(_normalize_axis(axes[0], x)[0])
        normalized_axis.append(_normalize_axis(axes[1], y)[0])
        # transpose
        i = normalized_axis[0]
        while i < len(x.shape) - 1:
            x = C.swapaxes(x, i, i + 1)
            i += 1
        i = normalized_axis[1]
        while i > 0:
            y = C.swapaxes(y, i, i - 1)
            i -= 1
        result = C.times(x, y, output_rank=(len(y.shape) - 1)
                         if len(y.shape) > 1 else 1)
        if len(y_shape) == 2:
            result = squeeze(result, -1)
        return result
Example #9
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def dot(x, y):
    if len(x.shape) > 2 or len(y.shape) > 2:
        y_shape = int_shape(y)
        if len(y_shape) > 2:
            permutation = [len(y_shape) - 2]
            permutation += list(range(len(y_shape) - 2))
            permutation += [len(y_shape) - 1]
            y = C.transpose(y, perm=permutation)
        return C.times(x, y, len(y_shape) - 1)
    else:
        return C.times(x, y)
Example #10
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def gather(reference, indices):
    # There is a bug in cntk gather op which may cause crash.
    # We have made a fix but not catched in CNTK 2.1 release.
    # Will update with gather op in next release
    if _get_cntk_version() >= 2.2:
        return C.ops.gather(reference, indices)
    else:
        num_classes = reference.shape[0]
        one_hot_matrix = C.ops.one_hot(indices, num_classes)
        return C.times(one_hot_matrix, reference, output_rank=len(reference.shape) - 1)
Example #11
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def gather(reference, indices):
    # There is a bug in cntk gather op which may cause crash.
    # We have made a fix but not catched in CNTK 2.1 release.
    # Will update with gather op in next release
    if _get_cntk_version() >= 2.2:
        return C.ops.gather(reference, indices)
    else:
        num_classes = reference.shape[0]
        one_hot_matrix = C.ops.one_hot(indices, num_classes)
        return C.times(one_hot_matrix, reference, output_rank=len(reference.shape) - 1)
Example #12
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def dot(x, y):
    if len(x.shape) > 2 or len(y.shape) > 2:
        y_shape = int_shape(y)
        if len(y_shape) > 2:
            permutation = [len(y_shape) - 2]
            permutation += list(range(len(y_shape) - 2))
            permutation += [len(y_shape) - 1]
            y = C.transpose(y, perm=permutation)
        return C.times(x, y, len(y_shape) - 1)
    else:
        return C.times(x, y)
Example #13
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def batch_dot(x, y, axes=None):
    x_shape = int_shape(x)
    y_shape = int_shape(y)

    if isinstance(axes, int):
        axes = (axes, axes)
    if axes is None:
        # behaves like tf.batch_matmul as default
        axes = [len(x_shape) - 1, len(y_shape) - 2]

    if len(x_shape) == 2 and len(y_shape) == 2:
        return sum(x * y, axis=1, keepdims=True)
    else:
        if len(y_shape) == 2:
            y = expand_dims(y)

        normalized_axis = []
        normalized_axis.append(_normalize_axis(axes[0], x)[0])
        normalized_axis.append(_normalize_axis(axes[1], y)[0])
        # transpose
        i = normalized_axis[0]
        while i < len(x.shape) - 1:
            x = C.swapaxes(x, i, i + 1)
            i += 1
        i = normalized_axis[1]
        while i > 0:
            y = C.swapaxes(y, i, i - 1)
            i -= 1
        result = C.times(x, y, output_rank=(len(y.shape) - 1)
                         if len(y.shape) > 1 else 1)
        if len(y_shape) == 2:
            result = squeeze(result, -1)
        return result
Example #14
Source File: cntk_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def dot(x, y):
    if len(x.shape) > 2 or len(y.shape) > 2:
        y_shape = int_shape(y)
        if len(y_shape) > 2:
            permutation = [len(y_shape) - 2]
            permutation += list(range(0, len(y_shape) - 2))
            permutation += [len(y_shape) - 1]
            y = C.transpose(y, perm=permutation)
        return C.times(x, y, len(y_shape) - 1)
    else:
        return C.times(x, y)
Example #15
Source File: cntk_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def batch_dot(x, y, axes=None):
    x_shape = int_shape(x)
    y_shape = int_shape(y)

    if isinstance(axes, int):
        axes = (axes, axes)
    if axes is None:
        # behaves like tf.batch_matmul as default
        axes = [len(x_shape) - 1, len(y_shape) - 2]

    if len(x_shape) == 2 and len(y_shape) == 2:
        return sum(x * y, axis=1, keepdims=True)
    else:
        if len(y_shape) == 2:
            y = expand_dims(y)

        normalized_axis = []
        normalized_axis.append(_normalize_axis(axes[0], x)[0])
        normalized_axis.append(_normalize_axis(axes[1], y)[0])
        # transpose
        i = normalized_axis[0]
        while i < len(x.shape) - 1:
            x = C.swapaxes(x, i, i + 1)
            i += 1
        i = normalized_axis[1]
        while i > 0:
            y = C.swapaxes(y, i, i - 1)
            i -= 1
        result = C.times(x, y, output_rank=(len(y.shape) - 1)
                         if len(y.shape) > 1 else 1)
        if len(y_shape) == 2:
            result = squeeze(result, -1)
        return result
Example #16
Source File: cntk_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def gather(reference, indices):
    # There is a bug in cntk gather op which may cause crash.
    # We have made a fix but not catched in CNTK 2.1 release.
    # Will udpate with gather op in next release
    if _get_cntk_version() >= 2.2:
        return C.ops.gather(reference, indices)
    else:
        num_class = reference.shape[0]
        one_hot_matrix = C.ops.one_hot(indices, num_class)
        return C.times(one_hot_matrix, reference, output_rank=len(reference.shape) - 1)
Example #17
Source File: cntk_backend.py    From keras-lambda with MIT License 5 votes vote down vote up 
def dot(x, y):
    if len(x.shape) > 2 or len(y.shape) > 2:
        y_shape = int_shape(y)
        if len(y_shape) > 2:
            permutation = [len(y_shape) - 2]
            permutation += list(range(0, len(y_shape) - 2))
            permutation += [len(y_shape) - 1]
            y = C.transpose(y, perm=permutation)
        return C.times(x, y, len(y_shape) - 1)
    else:
        return C.times(x, y)
Example #18
Source File: cntk_backend.py    From keras-lambda with MIT License 5 votes vote down vote up 
def batch_dot(x, y, axes=None):
    x_shape = int_shape(x)
    y_shape = int_shape(y)

    if isinstance(axes, int):
        axes = (axes, axes)
    if axes is None:
        # behaves like tf.batch_matmul as default
        axes = [len(x_shape) - 1, len(y_shape) - 2]

    if len(x_shape) == 2 and len(y_shape) == 2:
        return sum(x * y, axis=1, keepdims=True)
    else:
        if len(y_shape) == 2:
            y = expand_dims(y)

        normalized_axis = []
        normalized_axis.append(_normalize_axis(axes[0], x)[0])
        normalized_axis.append(_normalize_axis(axes[1], y)[0])
        # transpose
        i = normalized_axis[0]
        while i < len(x.shape) - 1:
            x = C.swapaxes(x, i, i + 1)
            i += 1
        i = normalized_axis[1]
        while i > 0:
            y = C.swapaxes(y, i, i - 1)
            i -= 1
        result = C.times(x, y, output_rank=(len(y.shape) - 1)
                         if len(y.shape) > 1 else 1)
        if len(y_shape) == 2:
            result = squeeze(result, -1)
        return result
Example #19
Source File: cntk_backend.py    From GraphicDesignPatternByPython with MIT License 5 votes vote down vote up 
def gather(reference, indices):
    # There is a bug in cntk gather op which may cause crash.
    # We have made a fix but not catched in CNTK 2.1 release.
    # Will update with gather op in next release
    if _get_cntk_version() >= 2.2:
        return C.ops.gather(reference, indices)
    else:
        num_classes = reference.shape[0]
        one_hot_matrix = C.ops.one_hot(indices, num_classes)
        return C.times(one_hot_matrix, reference, output_rank=len(reference.shape) - 1)
Example #20
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 #21
Source File: test_ops_binary.py    From ngraph-python with Apache License 2.0 5 votes vote down vote up 
def test_times_1():
    cntk_op = C.times([1, 2, 3], [[4], [5], [6]])
    cntk_ret = cntk_op.eval()

    ng_op, _ = CNTKImporter().import_model(cntk_op)
    ng_ret = ng.transformers.make_transformer().computation(ng_op)()

    assert np.array_equiv(cntk_ret, ng_ret)
Example #22
Source File: test_ops_binary.py    From ngraph-python with Apache License 2.0 5 votes vote down vote up 
def test_times_2():
    cntk_op = C.times([[1, 2], [3, 4]], [[5, 6], [7, 8]])
    cntk_ret = cntk_op.eval()

    ng_op, _ = CNTKImporter().import_model(cntk_op)
    ng_ret = ng.transformers.make_transformer().computation(ng_op)()

    assert np.array_equiv(cntk_ret, ng_ret)
Example #23
Source File: test_ops_binary.py    From ngraph-python with Apache License 2.0 5 votes vote down vote up 
def test_times_3():
    cntk_op = C.times([1, 2, 3], [[4, 5], [6, 7], [8, 9]])
    cntk_ret = cntk_op.eval()

    ng_op, _ = CNTKImporter().import_model(cntk_op)
    ng_ret = ng.transformers.make_transformer().computation(ng_op)()

    assert np.array_equiv(cntk_ret, ng_ret)
Example #24
Source File: test_ops_binary.py    From ngraph-python with Apache License 2.0 5 votes vote down vote up 
def test_times_5():
    cntk_op = C.times([[1, 2, 3], [4, 5, 6]], [[7, 8], [9, 10], [11, 12]])
    cntk_ret = cntk_op.eval()

    ng_op, _ = CNTKImporter().import_model(cntk_op)
    ng_ret = ng.transformers.make_transformer().computation(ng_op)()

    assert np.array_equiv(cntk_ret, ng_ret)
Example #25
Source File: test_ops_binary.py    From ngraph-python with Apache License 2.0 5 votes vote down vote up 
def test_times_6():
    cntk_op = C.times([[1, 2], [3, 4], [5, 6]], [[7, 8, 9], [10, 11, 12]])
    cntk_ret = cntk_op.eval()

    ng_op, _ = CNTKImporter().import_model(cntk_op)
    ng_ret = ng.transformers.make_transformer().computation(ng_op)()

    assert np.array_equiv(cntk_ret, ng_ret)
Example #26
Source File: cntk_backend.py    From GraphicDesignPatternByPython with MIT License 5 votes vote down vote up 
def dot(x, y):
    if len(x.shape) > 2 or len(y.shape) > 2:
        y_shape = int_shape(y)
        if len(y_shape) > 2:
            permutation = [len(y_shape) - 2]
            permutation += list(range(len(y_shape) - 2))
            permutation += [len(y_shape) - 1]
            y = C.transpose(y, perm=permutation)
        return C.times(x, y, len(y_shape) - 1)
    else:
        return C.times(x, y)
Example #27
Source File: cntk_backend.py    From GraphicDesignPatternByPython with MIT License 5 votes vote down vote up 
def batch_dot(x, y, axes=None):
    x_shape = int_shape(x)
    y_shape = int_shape(y)

    if isinstance(axes, int):
        axes = (axes, axes)
    if axes is None:
        # behaves like tf.batch_matmul as default
        axes = [len(x_shape) - 1, len(y_shape) - 2]
    if b_any([isinstance(a, (list, tuple)) for a in axes]):
        raise ValueError('Multiple target dimensions are not supported. ' +
                         'Expected: None, int, (int, int), ' +
                         'Provided: ' + str(axes))

    if len(x_shape) == 2 and len(y_shape) == 2:
        if axes[0] == axes[1]:
            result = sum(x * y, axis=axes[0], keepdims=True)
            return result if axes[0] == 1 else transpose(result)
        else:
            return sum(x * transpose(y), axis=axes[0], keepdims=True)
    else:
        if len(y_shape) == 2:
            y = expand_dims(y)

        normalized_axis = []
        normalized_axis.append(_normalize_axis(axes[0], x)[0])
        normalized_axis.append(_normalize_axis(axes[1], y)[0])
        # transpose
        i = normalized_axis[0]
        while i < len(x.shape) - 1:
            x = C.swapaxes(x, i, i + 1)
            i += 1
        i = normalized_axis[1]
        while i > 0:
            y = C.swapaxes(y, i, i - 1)
            i -= 1
        result = C.times(x, y, output_rank=(len(y.shape) - 1)
                         if len(y.shape) > 1 else 1)
        if len(y_shape) == 2:
            result = squeeze(result, -1)
        return result
Example #28
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 #29
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def dot(x, y):
    if len(x.shape) > 2 or len(y.shape) > 2:
        y_shape = int_shape(y)
        if len(y_shape) > 2:
            permutation = [len(y_shape) - 2]
            permutation += list(range(len(y_shape) - 2))
            permutation += [len(y_shape) - 1]
            y = C.transpose(y, perm=permutation)
        return C.times(x, y, len(y_shape) - 1)
    else:
        return C.times(x, y)
Example #30
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def batch_dot(x, y, axes=None):
    x_shape = int_shape(x)
    y_shape = int_shape(y)

    if isinstance(axes, int):
        axes = (axes, axes)
    if axes is None:
        # behaves like tf.batch_matmul as default
        axes = [len(x_shape) - 1, len(y_shape) - 2]

    if len(x_shape) == 2 and len(y_shape) == 2:
        return sum(x * y, axis=1, keepdims=True)
    else:
        if len(y_shape) == 2:
            y = expand_dims(y)

        normalized_axis = []
        normalized_axis.append(_normalize_axis(axes[0], x)[0])
        normalized_axis.append(_normalize_axis(axes[1], y)[0])
        # transpose
        i = normalized_axis[0]
        while i < len(x.shape) - 1:
            x = C.swapaxes(x, i, i + 1)
            i += 1
        i = normalized_axis[1]
        while i > 0:
            y = C.swapaxes(y, i, i - 1)
            i -= 1
        result = C.times(x, y, output_rank=(len(y.shape) - 1)
                         if len(y.shape) > 1 else 1)
        if len(y_shape) == 2:
            result = squeeze(result, -1)
        return result