Python cntk.convolution() Examples

The following are 30 code examples of cntk.convolution(). 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 GraphicDesignPatternByPython with MIT License 6 votes vote down vote up 
def conv2d(x, kernel, strides=(1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1)):
    data_format = normalize_data_format(data_format)

    x = _preprocess_conv2d_input(x, data_format)
    kernel = _preprocess_conv2d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)

    if dev.type() == 0 and dilation_rate != (1, 1):
        raise ValueError('Dilated convolution on CPU is not supported by CNTK backend. '
                         'Please set `dilation_rate` to (1, 1). '
                         'You passed: %s' % (dilation_rate,))

    dilation_rate = (1,) + dilation_rate

    x = C.convolution(kernel,
                      x,
                      strides,
                      auto_padding=[False, padding, padding],
                      dilation=dilation_rate)

    return _postprocess_conv2d_output(x, data_format)
Example #2
Source File: cntk_backend.py    From keras-lambda with MIT License 6 votes vote down vote up 
def conv3d(x, kernel, strides=(1, 1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv3d_input(x, data_format)
    kernel = _preprocess_conv3d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    strides = strides + (strides[0],)

    x = C.convolution(
        kernel,
        x,
        strides,
        auto_padding=[
            False,
            padding,
            padding,
            padding])
    return _postprocess_conv3d_output(x, data_format)
Example #3
Source File: cntk_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up 
def conv3d(x, kernel, strides=(1, 1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv3d_input(x, data_format)
    kernel = _preprocess_conv3d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    strides = strides + (strides[0],)

    x = C.convolution(
        kernel,
        x,
        strides,
        auto_padding=[
            False,
            padding,
            padding,
            padding])
    return _postprocess_conv3d_output(x, data_format)
Example #4
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 6 votes vote down vote up 
def conv3d(x, kernel, strides=(1, 1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv3d_input(x, data_format)
    kernel = _preprocess_conv3d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    strides = strides + (strides[0],)

    x = C.convolution(
        kernel,
        x,
        strides,
        auto_padding=[
            False,
            padding,
            padding,
            padding])
    return _postprocess_conv3d_output(x, data_format)
Example #5
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 6 votes vote down vote up 
def conv3d(x, kernel, strides=(1, 1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv3d_input(x, data_format)
    kernel = _preprocess_conv3d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    strides = strides + (strides[0],)

    x = C.convolution(
        kernel,
        x,
        strides,
        auto_padding=[
            False,
            padding,
            padding,
            padding])
    return _postprocess_conv3d_output(x, data_format)
Example #6
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 6 votes vote down vote up 
def conv3d(x, kernel, strides=(1, 1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv3d_input(x, data_format)
    kernel = _preprocess_conv3d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    strides = strides + (strides[0],)

    x = C.convolution(
        kernel,
        x,
        strides,
        auto_padding=[
            False,
            padding,
            padding,
            padding])
    return _postprocess_conv3d_output(x, data_format)
Example #7
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 6 votes vote down vote up 
def conv3d(x, kernel, strides=(1, 1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv3d_input(x, data_format)
    kernel = _preprocess_conv3d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    strides = strides + (strides[0],)

    x = C.convolution(
        kernel,
        x,
        strides,
        auto_padding=[
            False,
            padding,
            padding,
            padding])
    return _postprocess_conv3d_output(x, data_format)
Example #8
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 6 votes vote down vote up 
def conv3d(x, kernel, strides=(1, 1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv3d_input(x, data_format)
    kernel = _preprocess_conv3d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    strides = strides + (strides[0],)

    x = C.convolution(
        kernel,
        x,
        strides,
        auto_padding=[
            False,
            padding,
            padding,
            padding])
    return _postprocess_conv3d_output(x, data_format)
Example #9
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 6 votes vote down vote up 
def conv3d(x, kernel, strides=(1, 1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv3d_input(x, data_format)
    kernel = _preprocess_conv3d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    strides = strides + (strides[0],)

    x = C.convolution(
        kernel,
        x,
        strides,
        auto_padding=[
            False,
            padding,
            padding,
            padding])
    return _postprocess_conv3d_output(x, data_format)
Example #10
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 6 votes vote down vote up 
def conv3d(x, kernel, strides=(1, 1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv3d_input(x, data_format)
    kernel = _preprocess_conv3d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    strides = strides + (strides[0],)

    x = C.convolution(
        kernel,
        x,
        strides,
        auto_padding=[
            False,
            padding,
            padding,
            padding])
    return _postprocess_conv3d_output(x, data_format)
Example #11
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def conv2d(x, kernel, strides=(1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    kernel = _preprocess_conv2d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(
            kernel,
            x,
            strides,
            auto_padding=[
                False,
                padding,
                padding])
    else:
        assert dilation_rate[0] == dilation_rate[1]
        assert strides == (1, 1), 'Invalid strides for dilated convolution'
        x = C.convolution(
            kernel,
            x,
            strides=dilation_rate[0],
            auto_padding=[
                False,
                padding,
                padding])
    return _postprocess_conv2d_output(x, data_format)
Example #12
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def depthwise_conv2d(x, depthwise_kernel, strides=(1, 1), padding='valid',
                     data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    depthwise_kernel = _preprocess_conv2d_kernel(depthwise_kernel, data_format)
    depthwise_kernel = C.reshape(C.transpose(depthwise_kernel, (1, 0, 2, 3)),
                                 (-1, 1) + depthwise_kernel.shape[2:])
    padding = _preprocess_border_mode(padding)
    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(depthwise_kernel, x,
                          strides=strides,
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
    else:
        if dilation_rate[0] != dilation_rate[1]:
            raise ValueError('CNTK Backend: non-square dilation_rate is '
                             'not supported.')
        if strides != (1, 1):
            raise ValueError('Invalid strides for dilated convolution')
        x = C.convolution(depthwise_kernel, x,
                          strides=dilation_rate[0],
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
    return _postprocess_conv2d_output(x, data_format)
Example #13
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def separable_conv2d(x, depthwise_kernel, pointwise_kernel, strides=(1, 1),
                     padding='valid', data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    depthwise_kernel = _preprocess_conv2d_kernel(depthwise_kernel, data_format)
    depthwise_kernel = C.reshape(C.transpose(depthwise_kernel, (1, 0, 2, 3)),
                                 (-1, 1) + depthwise_kernel.shape[2:])
    pointwise_kernel = _preprocess_conv2d_kernel(pointwise_kernel, data_format)
    padding = _preprocess_border_mode(padding)

    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(depthwise_kernel, x,
                          strides=strides,
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
        x = C.convolution(pointwise_kernel, x,
                          strides=(1, 1, 1),
                          auto_padding=[False])
    else:
        if dilation_rate[0] != dilation_rate[1]:
            raise ValueError('CNTK Backend: non-square dilation_rate is '
                             'not supported.')
        if strides != (1, 1):
            raise ValueError('Invalid strides for dilated convolution')
        x = C.convolution(depthwise_kernel, x,
                          strides=dilation_rate[0],
                          auto_padding=[False, padding, padding])
        x = C.convolution(pointwise_kernel, x,
                          strides=(1, 1, 1),
                          auto_padding=[False])
    return _postprocess_conv2d_output(x, data_format)
Example #14
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def depthwise_conv2d(x, depthwise_kernel, strides=(1, 1), padding='valid',
                     data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    depthwise_kernel = _preprocess_conv2d_kernel(depthwise_kernel, data_format)
    depthwise_kernel = C.reshape(C.transpose(depthwise_kernel, (1, 0, 2, 3)),
                                 (-1, 1) + depthwise_kernel.shape[2:])
    padding = _preprocess_border_mode(padding)
    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(depthwise_kernel, x,
                          strides=strides,
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
    else:
        if dilation_rate[0] != dilation_rate[1]:
            raise ValueError('CNTK Backend: non-square dilation_rate is '
                             'not supported.')
        if strides != (1, 1):
            raise ValueError('Invalid strides for dilated convolution')
        x = C.convolution(depthwise_kernel, x,
                          strides=dilation_rate[0],
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
    return _postprocess_conv2d_output(x, data_format)
Example #15
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def conv1d(x, kernel, strides=1, padding='valid',
           data_format=None, dilation_rate=1):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    if padding == 'causal':
        # causal (dilated) convolution:
        left_pad = dilation_rate * (kernel.shape[0] - 1)
        x = temporal_padding(x, (left_pad, 0))
        padding = 'valid'

    if data_format == 'channels_last':
        x = C.swapaxes(x, 0, 1)
        kernel = C.swapaxes(kernel, 0, 2)

    padding = _preprocess_border_mode(padding)
    strides = [strides]
    x = C.convolution(
        kernel,
        x,
        strides=tuple(strides),
        auto_padding=[
            False,
            padding])

    if data_format == 'channels_last':
        x = C.swapaxes(x, 0, 1)
    return x
Example #16
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def conv2d(x, kernel, strides=(1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    kernel = _preprocess_conv2d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(
            kernel,
            x,
            strides,
            auto_padding=[
                False,
                padding,
                padding])
    else:
        assert dilation_rate[0] == dilation_rate[1]
        assert strides == (1, 1), 'Invalid strides for dilated convolution'
        x = C.convolution(
            kernel,
            x,
            strides=dilation_rate[0],
            auto_padding=[
                False,
                padding,
                padding])
    return _postprocess_conv2d_output(x, data_format)
Example #17
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def separable_conv2d(x, depthwise_kernel, pointwise_kernel, strides=(1, 1),
                     padding='valid', data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    depthwise_kernel = _preprocess_conv2d_kernel(depthwise_kernel, data_format)
    depthwise_kernel = C.reshape(C.transpose(depthwise_kernel, (1, 0, 2, 3)),
                                 (-1, 1) + depthwise_kernel.shape[2:])
    pointwise_kernel = _preprocess_conv2d_kernel(pointwise_kernel, data_format)
    padding = _preprocess_border_mode(padding)

    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(depthwise_kernel, x,
                          strides=strides,
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
        x = C.convolution(pointwise_kernel, x,
                          strides=(1, 1, 1),
                          auto_padding=[False])
    else:
        if dilation_rate[0] != dilation_rate[1]:
            raise ValueError('CNTK Backend: non-square dilation_rate is '
                             'not supported.')
        if strides != (1, 1):
            raise ValueError('Invalid strides for dilated convolution')
        x = C.convolution(depthwise_kernel, x,
                          strides=dilation_rate[0],
                          auto_padding=[False, padding, padding])
        x = C.convolution(pointwise_kernel, x,
                          strides=(1, 1, 1),
                          auto_padding=[False])
    return _postprocess_conv2d_output(x, data_format)
Example #18
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def depthwise_conv2d(x, depthwise_kernel, strides=(1, 1), padding='valid',
                     data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    depthwise_kernel = _preprocess_conv2d_kernel(depthwise_kernel, data_format)
    depthwise_kernel = C.reshape(C.transpose(depthwise_kernel, (1, 0, 2, 3)),
                                 (-1, 1) + depthwise_kernel.shape[2:])
    padding = _preprocess_border_mode(padding)
    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(depthwise_kernel, x,
                          strides=strides,
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
    else:
        if dilation_rate[0] != dilation_rate[1]:
            raise ValueError('CNTK Backend: non-square dilation_rate is '
                             'not supported.')
        if strides != (1, 1):
            raise ValueError('Invalid strides for dilated convolution')
        x = C.convolution(depthwise_kernel, x,
                          strides=dilation_rate[0],
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
    return _postprocess_conv2d_output(x, data_format)
Example #19
Source File: cntk_backend.py    From GraphicDesignPatternByPython with MIT License 5 votes vote down vote up 
def depthwise_conv2d(x, depthwise_kernel, strides=(1, 1), padding='valid',
                     data_format=None, dilation_rate=(1, 1)):
    data_format = normalize_data_format(data_format)

    x = _preprocess_conv2d_input(x, data_format)
    depthwise_kernel = _preprocess_conv2d_kernel(depthwise_kernel, data_format)
    depthwise_kernel = C.reshape(C.transpose(depthwise_kernel, (1, 0, 2, 3)),
                                 (-1, 1) + depthwise_kernel.shape[2:])
    padding = _preprocess_border_mode(padding)
    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(depthwise_kernel, x,
                          strides=strides,
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
    else:
        if dilation_rate[0] != dilation_rate[1]:
            raise ValueError('CNTK Backend: non-square dilation_rate is '
                             'not supported.')
        if strides != (1, 1):
            raise ValueError('Invalid strides for dilated convolution')
        x = C.convolution(depthwise_kernel, x,
                          strides=dilation_rate[0],
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
    return _postprocess_conv2d_output(x, data_format)
Example #20
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def conv2d(x, kernel, strides=(1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    kernel = _preprocess_conv2d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(
            kernel,
            x,
            strides,
            auto_padding=[
                False,
                padding,
                padding])
    else:
        assert dilation_rate[0] == dilation_rate[1]
        assert strides == (1, 1), 'Invalid strides for dilated convolution'
        x = C.convolution(
            kernel,
            x,
            strides=dilation_rate[0],
            auto_padding=[
                False,
                padding,
                padding])
    return _postprocess_conv2d_output(x, data_format)
Example #21
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def separable_conv2d(x, depthwise_kernel, pointwise_kernel, strides=(1, 1),
                     padding='valid', data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    depthwise_kernel = _preprocess_conv2d_kernel(depthwise_kernel, data_format)
    depthwise_kernel = C.reshape(C.transpose(depthwise_kernel, (1, 0, 2, 3)),
                                 (-1, 1) + depthwise_kernel.shape[2:])
    pointwise_kernel = _preprocess_conv2d_kernel(pointwise_kernel, data_format)
    padding = _preprocess_border_mode(padding)

    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(depthwise_kernel, x,
                          strides=strides,
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
        x = C.convolution(pointwise_kernel, x,
                          strides=(1, 1, 1),
                          auto_padding=[False])
    else:
        if dilation_rate[0] != dilation_rate[1]:
            raise ValueError('CNTK Backend: non-square dilation_rate is '
                             'not supported.')
        if strides != (1, 1):
            raise ValueError('Invalid strides for dilated convolution')
        x = C.convolution(depthwise_kernel, x,
                          strides=dilation_rate[0],
                          auto_padding=[False, padding, padding])
        x = C.convolution(pointwise_kernel, x,
                          strides=(1, 1, 1),
                          auto_padding=[False])
    return _postprocess_conv2d_output(x, data_format)
Example #22
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def depthwise_conv2d(x, depthwise_kernel, strides=(1, 1), padding='valid',
                     data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    depthwise_kernel = _preprocess_conv2d_kernel(depthwise_kernel, data_format)
    depthwise_kernel = C.reshape(C.transpose(depthwise_kernel, (1, 0, 2, 3)),
                                 (-1, 1) + depthwise_kernel.shape[2:])
    padding = _preprocess_border_mode(padding)
    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(depthwise_kernel, x,
                          strides=strides,
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
    else:
        if dilation_rate[0] != dilation_rate[1]:
            raise ValueError('CNTK Backend: non-square dilation_rate is '
                             'not supported.')
        if strides != (1, 1):
            raise ValueError('Invalid strides for dilated convolution')
        x = C.convolution(depthwise_kernel, x,
                          strides=dilation_rate[0],
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
    return _postprocess_conv2d_output(x, data_format)
Example #23
Source File: cntk_backend.py    From GraphicDesignPatternByPython with MIT License 5 votes vote down vote up 
def separable_conv2d(x, depthwise_kernel, pointwise_kernel, strides=(1, 1),
                     padding='valid', data_format=None, dilation_rate=(1, 1)):
    data_format = normalize_data_format(data_format)

    x = _preprocess_conv2d_input(x, data_format)
    depthwise_kernel = _preprocess_conv2d_kernel(depthwise_kernel, data_format)
    depthwise_kernel = C.reshape(C.transpose(depthwise_kernel, (1, 0, 2, 3)),
                                 (-1, 1) + depthwise_kernel.shape[2:])
    pointwise_kernel = _preprocess_conv2d_kernel(pointwise_kernel, data_format)
    padding = _preprocess_border_mode(padding)

    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(depthwise_kernel, x,
                          strides=strides,
                          auto_padding=[False, padding, padding],
                          groups=x.shape[0])
        x = C.convolution(pointwise_kernel, x,
                          strides=(1, 1, 1),
                          auto_padding=[False])
    else:
        if dilation_rate[0] != dilation_rate[1]:
            raise ValueError('CNTK Backend: non-square dilation_rate is '
                             'not supported.')
        if strides != (1, 1):
            raise ValueError('Invalid strides for dilated convolution')
        x = C.convolution(depthwise_kernel, x,
                          strides=dilation_rate[0],
                          auto_padding=[False, padding, padding])
        x = C.convolution(pointwise_kernel, x,
                          strides=(1, 1, 1),
                          auto_padding=[False])
    return _postprocess_conv2d_output(x, data_format)
Example #24
Source File: cntk_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def conv1d(x, kernel, strides=1, padding='valid',
           data_format=None, dilation_rate=1):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    if padding == 'causal':
        # causal (dilated) convolution:
        left_pad = dilation_rate * (kernel.shape[0] - 1)
        x = temporal_padding(x, (left_pad, 0))
        padding = 'valid'

    if data_format == 'channels_last':
        x = C.swapaxes(x, 0, 1)
        kernel = C.swapaxes(kernel, 0, 2)

    padding = _preprocess_border_mode(padding)
    strides = [strides]
    x = C.convolution(
        kernel,
        x,
        strides=tuple(strides),
        auto_padding=[
            False,
            padding])

    if data_format == 'channels_last':
        x = C.swapaxes(x, 0, 1)
    return x
Example #25
Source File: cntk_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def conv2d(x, kernel, strides=(1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    kernel = _preprocess_conv2d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(
            kernel,
            x,
            strides,
            auto_padding=[
                False,
                padding,
                padding])
    else:
        assert dilation_rate[0] == dilation_rate[1]
        assert strides == (1, 1), 'Invalid strides for dilated convolution'
        x = C.convolution(
            kernel,
            x,
            strides=dilation_rate[0],
            auto_padding=[
                False,
                padding,
                padding])
    return _postprocess_conv2d_output(x, data_format)
Example #26
Source File: cntk_backend.py    From keras-lambda with MIT License 5 votes vote down vote up 
def conv1d(x, kernel, strides=1, padding='valid',
           data_format=None, dilation_rate=1):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    if padding == 'causal':
        # causal (dilated) convolution:
        left_pad = dilation_rate * (kernel.shape[0] - 1)
        x = temporal_padding(x, (left_pad, 0))
        padding = 'valid'

    if data_format == 'channels_last':
        x = C.swapaxes(x, 0, 1)
        kernel = C.swapaxes(kernel, 0, 2)

    padding = _preprocess_border_mode(padding)
    strides = [strides]
    x = C.convolution(
        kernel,
        x,
        strides=tuple(strides),
        auto_padding=[
            False,
            padding])

    if data_format == 'channels_last':
        x = C.swapaxes(x, 0, 1)
    return x
Example #27
Source File: cntk_backend.py    From keras-lambda with MIT License 5 votes vote down vote up 
def conv2d(x, kernel, strides=(1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    kernel = _preprocess_conv2d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(
            kernel,
            x,
            strides,
            auto_padding=[
                False,
                padding,
                padding])
    else:
        assert dilation_rate[0] == dilation_rate[1]
        assert strides == (1, 1), 'Invalid strides for dilated convolution'
        x = C.convolution(
            kernel,
            x,
            strides=dilation_rate[0],
            auto_padding=[
                False,
                padding,
                padding])
    return _postprocess_conv2d_output(x, data_format)
Example #28
Source File: cntk_backend.py    From GraphicDesignPatternByPython with MIT License 5 votes vote down vote up 
def conv1d(x, kernel, strides=1, padding='valid',
           data_format=None, dilation_rate=1):
    data_format = normalize_data_format(data_format)

    if padding == 'causal':
        # causal (dilated) convolution:
        left_pad = dilation_rate * (kernel.shape[0] - 1)
        x = temporal_padding(x, (left_pad, 0))
        padding = 'valid'

    if data_format == 'channels_last':
        x = C.swapaxes(x, 0, 1)

    # As of Keras 2.0.0, all kernels are normalized
    # on the format `(steps, input_depth, depth)`,
    # independently of `data_format`.
    # CNTK expects `(depth, input_depth, steps)`.
    kernel = C.swapaxes(kernel, 0, 2)

    padding = _preprocess_border_mode(padding)

    if dev.type() == 0 and dilation_rate != 1:
        raise ValueError('Dilated convolution on CPU is not supported by CNTK backend. '
                         'Please set `dilation_rate` to 1. You passed: %s' % (dilation_rate,))

    dilation_rate = (1, dilation_rate)

    x = C.convolution(
        kernel,
        x,
        strides=strides,
        auto_padding=[False, padding],
        dilation=dilation_rate)

    if data_format == 'channels_last':
        x = C.swapaxes(x, 0, 1)
    return x
Example #29
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def conv2d(x, kernel, strides=(1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    kernel = _preprocess_conv2d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(
            kernel,
            x,
            strides,
            auto_padding=[
                False,
                padding,
                padding])
    else:
        assert dilation_rate[0] == dilation_rate[1]
        assert strides == (1, 1), 'Invalid strides for dilated convolution'
        x = C.convolution(
            kernel,
            x,
            strides=dilation_rate[0],
            auto_padding=[
                False,
                padding,
                padding])
    return _postprocess_conv2d_output(x, data_format)
Example #30
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def conv2d(x, kernel, strides=(1, 1), padding='valid',
           data_format=None, dilation_rate=(1, 1)):
    if data_format is None:
        data_format = image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    x = _preprocess_conv2d_input(x, data_format)
    kernel = _preprocess_conv2d_kernel(kernel, data_format)
    padding = _preprocess_border_mode(padding)
    if dilation_rate == (1, 1):
        strides = (1,) + strides
        x = C.convolution(
            kernel,
            x,
            strides,
            auto_padding=[
                False,
                padding,
                padding])
    else:
        assert dilation_rate[0] == dilation_rate[1]
        assert strides == (1, 1), 'Invalid strides for dilated convolution'
        x = C.convolution(
            kernel,
            x,
            strides=dilation_rate[0],
            auto_padding=[
                False,
                padding,
                padding])
    return _postprocess_conv2d_output(x, data_format)