本文整理汇总了Python中cntk.transpose方法的典型用法代码示例。如果您正苦于以下问题:Python cntk.transpose方法的具体用法?Python cntk.transpose怎么用?Python cntk.transpose使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类cntk
的用法示例。
在下文中一共展示了cntk.transpose方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: permute_dimensions
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
def permute_dimensions(x, pattern):
dims = len(int_shape(x))
num_dynamic_axis = _get_dynamic_axis_num(x)
if isinstance(pattern, list):
current_layout = [i for i in range(dims)]
else:
current_layout = tuple([i for i in range(dims)])
if num_dynamic_axis > 0 and pattern[:num_dynamic_axis] != current_layout[:num_dynamic_axis]:
raise ValueError('CNTK backend: the permute pattern %s '
'requested permute on dynamic axis, '
'which is not supported. Please do permute '
'on static axis.' % pattern)
axis = list(pattern)
axis = axis[num_dynamic_axis:]
axis = _normalize_axis(axis, x)
return C.transpose(x, axis)
示例2: local_conv1d
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
def local_conv1d(inputs, kernel, kernel_size, strides, data_format=None):
data_format = normalize_data_format(data_format)
stride = strides[0]
kernel_shape = int_shape(kernel)
output_length, feature_dim, filters = kernel_shape
xs = []
for i in range(output_length):
slice_length = py_slice(i * stride,
i * stride + kernel_size[0])
xs.append(reshape(inputs[:, slice_length, :],
(-1, 1, feature_dim)))
x_aggregate = concatenate(xs, axis=1)
# transpose kernel to output_filters first, to apply broadcast
weight = permute_dimensions(kernel, (2, 0, 1))
# Shape: (batch, filters, output_length, input_length * kernel_size)
output = x_aggregate * weight
# Shape: (batch, filters, output_length)
output = sum(output, axis=3)
# Shape: (batch, output_length, filters)
return permute_dimensions(output, (0, 2, 1))
示例3: _layer_Conv
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
def _layer_Conv(self):
self.add_body(0, """
def convolution(input, is_transpose, name, **kwargs):
dim = __weights_dict[name]['weights'].ndim
if is_transpose:
weight = np.transpose(__weights_dict[name]['weights'], [dim - 2, dim - 1] + list(range(0, dim - 2)))
kwargs.pop('groups', None)
else:
weight = np.transpose(__weights_dict[name]['weights'], [dim - 1, dim - 2] + list(range(0, dim - 2)))
w = cntk.Parameter(init=weight, name=name + '_weight')
input = cntk.transpose(input, [dim - 2] + list(range(0, dim - 2)))
if is_transpose:
layer = ops.convolution_transpose(w, input, **kwargs)
else:
layer = ops.convolution(w, input, **kwargs)
if 'bias' in __weights_dict[name]:
bias = np.reshape(__weights_dict[name]['bias'], [-1] + [1] * (dim - 2))
b = cntk.Parameter(init=bias, name=name + '_bias')
layer = layer + b
layer = cntk.transpose(layer, list(range(1, dim - 1)) + [0])
return layer
""")
示例4: local_conv1d
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
def local_conv1d(inputs, kernel, kernel_size, strides, data_format=None):
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))
stride = strides[0]
kernel_shape = int_shape(kernel)
output_length, feature_dim, filters = kernel_shape
xs = []
for i in range(output_length):
slice_length = slice(i * stride,
i * stride + kernel_size[0])
xs.append(reshape(inputs[:, slice_length, :],
(-1, 1, feature_dim)))
x_aggregate = concatenate(xs, axis=1)
# transpose kernel to output_filters first, to apply broadcast
weight = permute_dimensions(kernel, (2, 0, 1))
# Shape: (batch, filters, output_length, input_length * kernel_size)
output = x_aggregate * weight
# Shape: (batch, filters, output_length)
output = sum(output, axis=3)
# Shape: (batch, output_length, filters)
return permute_dimensions(output, (0, 2, 1))
示例5: dot
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
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)
示例6: batch_dot
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
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
示例7: transpose
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
def transpose(x):
return C.swapaxes(x, 0, 1)
示例8: depthwise_conv2d
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
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)
示例9: categorical_crossentropy
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
def categorical_crossentropy(target, output, from_logits=False, axis=-1):
# Here, unlike other backends, the tensors lack a batch dimension:
axis_without_batch = -1 if axis == -1 else axis - 1
output_dimensions = list(range(len(output.shape)))
if axis_without_batch != -1 and axis_without_batch not in output_dimensions:
raise ValueError(
'{}{}{}'.format(
'Unexpected channels axis {}. '.format(axis_without_batch),
'Expected to be -1 or one of the axes of `output`, ',
'which has {} dimensions.'.format(len(output.shape))))
# If the channels are not in the last axis, move them to be there:
if axis_without_batch != -1 and axis_without_batch != output_dimensions[-1]:
permutation = output_dimensions[:axis_without_batch]
permutation += output_dimensions[axis_without_batch + 1:]
permutation += [axis_without_batch]
output = C.transpose(output, permutation)
target = C.transpose(target, permutation)
if from_logits:
result = C.cross_entropy_with_softmax(output, target)
# cntk's result shape is (batch, 1), while keras expect (batch, )
return C.reshape(result, ())
else:
# scale preds so that the class probas of each sample sum to 1
output /= C.reduce_sum(output, axis=-1)
# avoid numerical instability with epsilon clipping
output = C.clip(output, epsilon(), 1.0 - epsilon())
return -sum(target * C.log(output), axis=-1)
示例10: _preprocess_conv2d_input
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
def _preprocess_conv2d_input(x, data_format):
if data_format == 'channels_last':
# TF uses the last dimension as channel dimension,
# instead of the 2nd one.
# TH input shape: (samples, input_depth, rows, cols)
# TF input shape: (samples, rows, cols, input_depth)
x = C.transpose(x, (2, 0, 1))
return x
示例11: _preprocess_conv2d_kernel
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
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`.
# CNTK expects `(depth, input_depth, rows, cols)`.
kernel = C.transpose(kernel, (3, 2, 0, 1))
return kernel
示例12: _postprocess_conv2d_output
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
def _postprocess_conv2d_output(x, data_format):
if data_format == 'channels_last':
x = C.transpose(x, (1, 2, 0))
return x
示例13: _preprocess_conv3d_kernel
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
def _preprocess_conv3d_kernel(kernel, dim_ordering):
kernel = C.transpose(kernel, (4, 3, 0, 1, 2))
return kernel
示例14: _postprocess_conv3d_output
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
def _postprocess_conv3d_output(x, dim_ordering):
if dim_ordering == 'channels_last':
x = C.transpose(x, (1, 2, 3, 0))
return x
示例15: _layer_Crop
# 需要导入模块: import cntk [as 别名]
# 或者: from cntk import transpose [as 别名]
def _layer_Crop(self):
self.add_body(0, '''
def _crop(input, border, output_shape, **kwargs):
dim = len(output_shape)
output_shape = [output_shape[-1]] + output_shape[:-1]
ref_tensor = np.zeros(shape=output_shape, dtype=np.float32)
input = cntk.transpose(input, [dim - 1] + list(range(0, dim - 1)))
layer = cntk.crop_manual(node_input=input, node_referent=ref_tensor, offset_x=border[0], offset_y=border[1])
layer = cntk.transpose(layer, list(range(1, dim)) + [0])
return layer
''')