Python backend.min方法代码示例

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import min [as 别名]
def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import min [as 别名]
def _correct_boxes(
            self, box_xy, box_wh, input_shape, image_shape):
        """Get corrected boxes, which are scaled to original shape."""
        box_yx = box_xy[..., ::-1]
        box_hw = box_wh[..., ::-1]
        input_shape = K.cast(input_shape, K.dtype(box_yx))
        image_shape = K.cast(image_shape, K.dtype(box_yx))
        new_shape = K.round(image_shape * K.min(input_shape / image_shape))
        offset = (input_shape - new_shape) / 2. / input_shape
        scale = input_shape / new_shape
        box_yx = (box_yx - offset) * scale
        box_hw *= scale

        box_mins = box_yx - (box_hw / 2.)
        box_maxes = box_yx + (box_hw / 2.)
        boxes = K.concatenate([
            box_mins[..., 0:1],  # y_min
            box_mins[..., 1:2],  # x_min
            box_maxes[..., 0:1],  # y_max
            box_maxes[..., 1:2]  # x_max
        ])

        # Scale boxes back to original image shape.
        boxes *= K.concatenate([image_shape, image_shape])
        return boxes 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import min [as 别名]
def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):

    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],
        box_mins[..., 1:2],
        box_maxes[..., 0:1],
        box_maxes[..., 1:2]
    ])


    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import min [as 别名]
def correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''

    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape / image_shape))
    offset = (input_shape - new_shape) / 2. / input_shape
    scale = input_shape / new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes = K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import min [as 别名]
def approximate_gaussian_ground_truth_image(image_shape, center, grasp_theta, grasp_width, grasp_height, label, sigma_divisor=None):
    """ Gaussian "ground truth" image approximation for a single proposed grasp at a time.

        For use with the Cornell grasping dataset

       see also: ground_truth_images() in cornell_grasp_dataset_writer.py
    """
    if sigma_divisor is None:
        sigma_divisor = FLAGS.sigma_divisor
    grasp_dims = keras.backend.concatenate([grasp_width, grasp_height])
    sigma = keras.backend.max(grasp_dims) / sigma_divisor

    # make sure center value for gaussian is 0.5
    gaussian = gaussian_kernel_2D(image_shape[:2], center=center, sigma=sigma)
    # label 0 is grasp failure, label 1 is grasp success, label 0.5 will have "no effect".
    # gaussian center with label 0 should be subtracting 0.5
    # gaussian center with label 1 should be adding 0.5
    gaussian = ((label * 2) - 1.0) * gaussian
    max_num = K.max(K.max(gaussian), K.placeholder(1.0))
    min_num = K.min(K.min(gaussian), K.placeholder(-1.0))
    gaussian = (gaussian - min_num) / (max_num - min_num)
    return gaussian 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import min [as 别名]
def call(self, inputs):
        """This is where the layer's logic lives.

        Parameters
        ----------
        inputs: tensor
            Input tensor, or list/tuple of input tensors
        kwargs: dict
            Additional keyword arguments

        Returns
        -------
        tensor
            A tensor or list/tuple of tensors
        """
        if self.data_format == 'channels_last':
            pooled = K.min(inputs, axis=[1, 2])
        else:
            pooled = K.min(inputs, axis=[2, 3])
        return pooled 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import min [as 别名]
def step(self, input_energy_t, states, return_logZ=True):
        # not in the following  `prev_target_val` has shape = (B, F)
        # where B = batch_size, F = output feature dim
        # Note: `i` is of float32, due to the behavior of `K.rnn`
        prev_target_val, i, chain_energy = states[:3]
        t = K.cast(i[0, 0], dtype='int32')
        if len(states) > 3:
            if K.backend() == 'theano':
                m = states[3][:, t:(t + 2)]
            else:
                m = K.tf.slice(states[3], [0, t], [-1, 2])
            input_energy_t = input_energy_t * K.expand_dims(m[:, 0])
            chain_energy = chain_energy * K.expand_dims(K.expand_dims(m[:, 0] * m[:, 1]))  # (1, F, F)*(B, 1, 1) -> (B, F, F)
        if return_logZ:
            energy = chain_energy + K.expand_dims(input_energy_t - prev_target_val, 2)  # shapes: (1, B, F) + (B, F, 1) -> (B, F, F)
            new_target_val = K.logsumexp(-energy, 1)  # shapes: (B, F)
            return new_target_val, [new_target_val, i + 1]
        else:
            energy = chain_energy + K.expand_dims(input_energy_t + prev_target_val, 2)
            min_energy = K.min(energy, 1)
            argmin_table = K.cast(K.argmin(energy, 1), K.floatx())  # cast for tf-version `K.rnn`
            return argmin_table, [min_energy, i + 1] 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import min [as 别名]
def ranking_loss_with_margin(y_pred, y_true):
    """
    Using this loss trains the model to give scores to all correct elements in y_true that are
    higher than all scores it gives to incorrect elements in y_true, plus a margin.

    For example, let ``y_true = [0, 0, 1, 1, 0]``, and let ``y_pred = [-1, 1, 2, 0, -2]``.  We will
    find the lowest score assigned to correct elements in ``y_true`` (``0`` in this case), and the
    highest score assigned to incorrect elements in ``y_true`` (``1`` in this case).  We will then
    compute a hinge loss given these values: ``K.maximum(0.0, 1 + 1 - 0)``.

    Note that the way we do this uses ``K.max()`` and ``K.min()`` over the elements in ``y_true``,
    which means that if you have a lot of values in here, you'll only get gradients backpropping
    through two of them (the ones on the margin).  This could be an inefficient use of your
    computation time.  Think carefully about the data that you're using with this loss function.

    Because of the way masking works with Keras loss functions, also, you need to be sure that any
    masked elements in ``y_pred`` have very negative values before they get passed into this loss
    function.
    """
    correct_elements = y_pred + (1.0 - y_true) * VERY_LARGE_NUMBER
    lowest_scoring_correct = K.min(correct_elements, axis=-1)
    incorrect_elements = y_pred + y_true * VERY_NEGATIVE_NUMBER
    highest_scoring_incorrect = K.max(incorrect_elements, axis=-1)
    return K.mean(K.maximum(0.0, 1.0 + highest_scoring_incorrect - lowest_scoring_correct))