Python tensor.nnet方法代码示例

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def batch_normalization(x, mean, var, beta, gamma, epsilon=1e-3):
    '''Apply batch normalization on x given mean, var, beta and gamma.
    '''
    # TODO remove this if statement when Theano without
    # T.nnet.bn.batch_normalization_test is deprecated
    if not hasattr(T.nnet.bn, 'batch_normalization_test'):
        return _old_batch_normalization(x, mean, var, beta, gamma, epsilon)

    if mean.ndim == 1:
        # based on TensorFlow's default: normalize along rightmost dimension
        reduction_axes = range(x.ndim - 1)
    else:
        reduction_axes = [i for i in range(x.ndim) if mean.broadcastable[i]]

    return T.nnet.bn.batch_normalization_test(
        x, gamma, beta, mean, var, reduction_axes, epsilon)


# TODO remove this function when Theano without
# T.nnet.bn.batch_normalization_train is deprecated 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def normalize_batch_in_training(x, gamma, beta,
                                reduction_axes, epsilon=1e-3):
    """Computes mean and std for batch then apply batch_normalization on batch.
    """
    # TODO remove this if statement when Theano without
    # T.nnet.bn.batch_normalization_train is deprecated
    if not hasattr(T.nnet.bn, 'batch_normalization_train'):
        return _old_normalize_batch_in_training(x, gamma, beta, reduction_axes, epsilon)

    if gamma is None:
        if beta is None:
            gamma = ones_like(x)
        else:
            gamma = ones_like(beta)
    if beta is None:
        if gamma is None:
            beta = zeros_like(x)
        beta = zeros_like(gamma)

    normed, mean, stdinv = T.nnet.bn.batch_normalization_train(
        x, gamma, beta, reduction_axes, epsilon)

    return normed, mean, T.inv(stdinv ** 2) 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def batch_normalization(x, mean, var, beta, gamma, axis=-1, epsilon=1e-3):
    """Apply batch normalization on x given mean, var, beta and gamma.
    """
    # TODO remove this if statement when Theano without
    # T.nnet.bn.batch_normalization_test is deprecated
    if not hasattr(T.nnet.bn, 'batch_normalization_test'):
        return _old_batch_normalization(x, mean, var, beta, gamma, epsilon)

    if gamma is None:
        gamma = ones_like(var)
    if beta is None:
        beta = zeros_like(mean)

    if mean.ndim == 1:
        # based on TensorFlow's default: normalize along rightmost dimension
        reduction_axes = list(range(x.ndim - 1))
    else:
        reduction_axes = [i for i in range(x.ndim) if mean.broadcastable[i]]

    return T.nnet.bn.batch_normalization_test(
        x, gamma, beta, mean, var, reduction_axes, epsilon)


# TODO remove this function when Theano without
# T.nnet.bn.batch_normalization_train is deprecated 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def relu(x, alpha=0., max_value=None, threshold=0.):
    _assert_has_capability(T.nnet, 'relu')

    if alpha != 0.:
        if threshold != 0.:
            negative_part = T.nnet.relu(-x + threshold)
        else:
            negative_part = T.nnet.relu(-x)

    if threshold != 0.:
        x = x * T.cast(T.gt(x, threshold), floatx())
    else:
        x = T.nnet.relu(x)

    if max_value is not None:
        x = T.clip(x, 0.0, max_value)

    if alpha != 0.:
        x -= alpha * negative_part

    return x 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def categorical_crossentropy(target, output, from_logits=False, axis=-1):
    output_dimensions = list(range(len(int_shape(output))))
    if axis != -1 and axis not in output_dimensions:
        raise ValueError(
            '{}{}{}'.format(
                'Unexpected channels axis {}. '.format(axis),
                'Expected to be -1 or one of the axes of `output`, ',
                'which has {} dimensions.'.format(len(int_shape(output)))))
    # If the channels are not in the last axis, move them to be there:
    if axis != -1 and axis != output_dimensions[-1]:
        permutation = output_dimensions[:axis]
        permutation += output_dimensions[axis + 1:] + [axis]
        output = permute_dimensions(output, permutation)
        target = permute_dimensions(target, permutation)
    if from_logits:
        output = T.nnet.softmax(output)
    else:
        # scale preds so that the class probas of each sample sum to 1
        output /= output.sum(axis=-1, keepdims=True)
    # avoid numerical instability with _EPSILON clipping
    output = T.clip(output, epsilon(), 1.0 - epsilon())
    return T.nnet.categorical_crossentropy(output, target) 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def batch_normalization(x, mean, var, beta, gamma, epsilon=1e-3):
    """Apply batch normalization on x given mean, var, beta and gamma.
    """
    # TODO remove this if statement when Theano without
    # T.nnet.bn.batch_normalization_test is deprecated
    if not hasattr(T.nnet.bn, 'batch_normalization_test'):
        return _old_batch_normalization(x, mean, var, beta, gamma, epsilon)

    if gamma is None:
        gamma = ones_like(var)
    if beta is None:
        beta = zeros_like(mean)

    if mean.ndim == 1:
        # based on TensorFlow's default: normalize along rightmost dimension
        reduction_axes = list(range(x.ndim - 1))
    else:
        reduction_axes = [i for i in range(x.ndim) if mean.broadcastable[i]]

    return T.nnet.bn.batch_normalization_test(
        x, gamma, beta, mean, var, reduction_axes, epsilon)


# TODO remove this function when Theano without
# T.nnet.bn.batch_normalization_train is deprecated 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def normalize_batch_in_training(x, gamma, beta,
                                reduction_axes, epsilon=1e-3):
    '''Computes mean and std for batch then apply batch_normalization on batch.
    '''
    # TODO remove this if statement when Theano without
    # T.nnet.bn.batch_normalization_train is deprecated
    if not hasattr(T.nnet.bn, 'batch_normalization_train'):
        return _old_normalize_batch_in_training(x, gamma, beta, reduction_axes, epsilon)

    normed, mean, stdinv = T.nnet.bn.batch_normalization_train(
        x, gamma, beta, reduction_axes, epsilon)

    return normed, mean, T.inv(stdinv ** 2) 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def _old_normalize_batch_in_training(x, gamma, beta,
                                     reduction_axes, epsilon=1e-3):
    '''Computes mean and std for batch then apply batch_normalization on batch.
    '''
    dev = theano.config.device
    use_cudnn = ndim(x) < 5 and reduction_axes == [0, 2, 3] and (dev.startswith('cuda') or dev.startswith('gpu'))
    if use_cudnn:
        broadcast_beta = beta.dimshuffle('x', 0, 'x', 'x')
        broadcast_gamma = gamma.dimshuffle('x', 0, 'x', 'x')
        try:
            normed, mean, stdinv = theano.sandbox.cuda.dnn.dnn_batch_normalization_train(
                x, broadcast_gamma, broadcast_beta, 'spatial', epsilon)
            var = T.inv(stdinv ** 2)
            return normed, T.flatten(mean), T.flatten(var)
        except AttributeError:
            pass

    var = x.var(reduction_axes)
    mean = x.mean(reduction_axes)

    target_shape = []
    for axis in range(ndim(x)):
        if axis in reduction_axes:
            target_shape.append(1)
        else:
            target_shape.append(x.shape[axis])
    target_shape = T.stack(*target_shape)

    broadcast_mean = T.reshape(mean, target_shape)
    broadcast_var = T.reshape(var, target_shape)
    broadcast_beta = T.reshape(beta, target_shape)
    broadcast_gamma = T.reshape(gamma, target_shape)
    normed = batch_normalization(x, broadcast_mean, broadcast_var,
                                 broadcast_beta, broadcast_gamma,
                                 epsilon)
    return normed, mean, var


# TODO remove this if statement when Theano without
# T.nnet.bn.batch_normalization_test is deprecated 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def elu(x, alpha=1.0):
    """ Exponential linear unit

    # Arguments
        x: Tensor to compute the activation function for.
        alpha: scalar
    """
    _assert_has_capability(T.nnet, 'elu')
    return T.nnet.elu(x, alpha) 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def softmax(x):
    return T.nnet.softmax(x) 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def softplus(x):
    return T.nnet.softplus(x) 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def categorical_crossentropy(output, target, from_logits=False):
    if from_logits:
        output = T.nnet.softmax(output)
    else:
        # scale preds so that the class probas of each sample sum to 1
        output /= output.sum(axis=-1, keepdims=True)
    # avoid numerical instability with _EPSILON clipping
    output = T.clip(output, _EPSILON, 1.0 - _EPSILON)
    return T.nnet.categorical_crossentropy(output, target) 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def binary_crossentropy(output, target, from_logits=False):
    if from_logits:
        output = T.nnet.sigmoid(output)
    # avoid numerical instability with _EPSILON clipping
    output = T.clip(output, _EPSILON, 1.0 - _EPSILON)
    return T.nnet.binary_crossentropy(output, target) 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def sigmoid(x):
    return T.nnet.sigmoid(x) 

# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import nnet [as 别名]
def deconv2d(x, kernel, output_shape, strides=(1, 1),
             border_mode='valid',
             dim_ordering='default',
             image_shape=None, filter_shape=None):
    '''2D deconvolution (transposed convolution).

    # Arguments
        kernel: kernel tensor.
        output_shape: desired dimensions of output.
        strides: strides tuple.
        border_mode: string, "same" or "valid".
        dim_ordering: "tf" or "th".
            Whether to use Theano or TensorFlow dimension ordering
        in inputs/kernels/ouputs.
    '''
    flip_filters = False
    if dim_ordering == 'default':
        dim_ordering = image_dim_ordering()
    if dim_ordering not in {'th', 'tf'}:
        raise ValueError('Unknown dim_ordering ' + dim_ordering)

    x = _preprocess_conv2d_input(x, dim_ordering)
    kernel = _preprocess_conv2d_kernel(kernel, dim_ordering)
    kernel = kernel.dimshuffle((1, 0, 2, 3))
    th_border_mode = _preprocess_border_mode(border_mode)
    np_kernel = kernel.eval()
    filter_shape = _preprocess_conv2d_filter_shape(dim_ordering, filter_shape)
    filter_shape = tuple(filter_shape[i] for i in (1, 0, 2, 3))

    op = T.nnet.abstract_conv.AbstractConv2d_gradInputs(imshp=output_shape,
                                                        kshp=filter_shape,
                                                        subsample=strides,
                                                        border_mode=th_border_mode,
                                                        filter_flip=not flip_filters)
    conv_out = op(kernel, x, output_shape[2:])

    conv_out = _postprocess_conv2d_output(conv_out, x, border_mode, np_kernel,
                                          strides, dim_ordering)
    return conv_out