Python cfg.PIXEL_MEANS属性代码示例

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import PIXEL_MEANS [as 别名]
def get_image_blob(im, target_scale, target_max_size):
    """Convert an image into a network input.

    Arguments:
        im (ndarray): a color image in BGR order

    Returns:
        blob (ndarray): a data blob holding an image pyramid
        im_scale (float): image scale (target size) / (original size)
        im_info (ndarray)
    """
    processed_im, im_scale = prep_im_for_blob(
        im, cfg.PIXEL_MEANS, [target_scale], target_max_size
    )
    blob = im_list_to_blob(processed_im)
    # NOTE: this height and width may be larger than actual scaled input image
    # due to the FPN.COARSEST_STRIDE related padding in im_list_to_blob. We are
    # maintaining this behavior for now to make existing results exactly
    # reproducible (in practice using the true input image height and width
    # yields nearly the same results, but they are sometimes slightly different
    # because predictions near the edge of the image will be pruned more
    # aggressively).
    height, width = blob.shape[2], blob.shape[3]
    im_info = np.hstack((height, width, im_scale))[np.newaxis, :]
    return blob, im_scale, im_info.astype(np.float32) 

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import PIXEL_MEANS [as 别名]
def get_image_blob(im, target_scale, target_max_size):
    """Convert an image into a network input.

    Arguments:
        im (ndarray): a color image in BGR order

    Returns:
        blob (ndarray): a data blob holding an image pyramid
        im_scale (float): image scale (target size) / (original size)
        im_info (ndarray)
    """
    processed_im, im_scale = prep_im_for_blob(
        im, cfg.PIXEL_MEANS, [target_scale], target_max_size
    )
    blob = im_list_to_blob(processed_im)

    return blob, im_scale 

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import PIXEL_MEANS [as 别名]
def get_image_blob(im, target_scale, target_max_size):
    """Convert an image into a network input.

    Arguments:
        im (ndarray): a color image in BGR order

    Returns:
        blob (ndarray): a data blob holding an image pyramid
        im_scale (float): image scale (target size) / (original size)
        im_info (ndarray)
    """
    processed_im, im_scale = prep_im_for_blob(
        im, cfg.PIXEL_MEANS, target_scale, target_max_size
    )
    blob = im_list_to_blob(processed_im)
    # NOTE: this height and width may be larger than actual scaled input image
    # due to the FPN.COARSEST_STRIDE related padding in im_list_to_blob. We are
    # maintaining this behavior for now to make existing results exactly
    # reproducible (in practice using the true input image height and width
    # yields nearly the same results, but they are sometimes slightly different
    # because predictions near the edge of the image will be pruned more
    # aggressively).
    height, width = blob.shape[2], blob.shape[3]
    im_info = np.hstack((height, width, im_scale))[np.newaxis, :]
    return blob, im_scale, im_info.astype(np.float32) 

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import PIXEL_MEANS [as 别名]
def _get_image_blob(im):
    """Converts an image into a network input.

    Arguments:
        im (ndarray): a color image in BGR order

    Returns:
        blob (ndarray): a data blob holding an image pyramid
        im_scale_factors (ndarray): array of image scales (relative to im) used
            in the image pyramid
    """
    processed_ims, im_scale_factors = blob_utils.prep_im_for_blob(
        im, cfg.PIXEL_MEANS, cfg.TEST.SCALES, cfg.TEST.MAX_SIZE
    )
    blob = blob_utils.im_list_to_blob(processed_ims)
    return blob, np.array(im_scale_factors) 

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import PIXEL_MEANS [as 别名]
def _get_image_blob(roidb):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    # Sample random scales to use for each image in this batch
    scale_inds = np.random.randint(
        0, high=len(cfg.TRAIN.SCALES), size=num_images)
    processed_ims = []
    im_scales = []
    for i in range(num_images):
        im = cv2.imread(roidb[i]['image'])
        assert im is not None, \
            'Failed to read image \'{}\''.format(roidb[i]['image'])
        # If NOT using opencv to read in images, uncomment following lines
        # if len(im.shape) == 2:
        #     im = im[:, :, np.newaxis]
        #     im = np.concatenate((im, im, im), axis=2)
        # # flip the channel, since the original one using cv2
        # # rgb -> bgr
        # im = im[:, :, ::-1]
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]
        target_size = cfg.TRAIN.SCALES[scale_inds[i]]
        im, im_scale = blob_utils.prep_im_for_blob(
            im, cfg.PIXEL_MEANS, [target_size], cfg.TRAIN.MAX_SIZE)
        im_scales.append(im_scale[0])
        processed_ims.append(im[0])

    # Create a blob to hold the input images [n, c, h, w]
    blob = blob_utils.im_list_to_blob(processed_ims)

    return blob, im_scales 

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import PIXEL_MEANS [as 别名]
def _get_image_blob(roidb):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    # Sample random scales to use for each image in this batch
    scale_inds = np.random.randint(
        0, high=len(cfg.TRAIN.SCALES), size=num_images
    )
    processed_ims = []
    im_scales = []
    for i in range(num_images):
        im = cv2.imread(roidb[i]['image'])
        assert im is not None, \
            'Failed to read image \'{}\''.format(roidb[i]['image'])
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]
        target_size = cfg.TRAIN.SCALES[scale_inds[i]]
        im, im_scale = blob_utils.prep_im_for_blob(
            im, cfg.PIXEL_MEANS, target_size, cfg.TRAIN.MAX_SIZE
        )
        im_scales.append(im_scale)
        processed_ims.append(im)

    # Create a blob to hold the input images
    blob = blob_utils.im_list_to_blob(processed_ims)

    return blob, im_scales 

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import PIXEL_MEANS [as 别名]
def _get_image_blob(roidb):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    # Sample random scales to use for each image in this batch
    scale_inds = np.random.randint(
        0, high=len(cfg.TRAIN.SCALES), size=num_images)
    processed_ims = []
    im_scales = []
    for i in range(num_images):
        im = cv2.imread(roidb[i]['image'])
        assert im is not None, \
            'Failed to read image \'{}\''.format(roidb[i]['image'])
        # If NOT using opencv to read in images, uncomment following lines
        # if len(im.shape) == 2:
        #     im = im[:, :, np.newaxis]
        #     im = np.concatenate((im, im, im), axis=2)
        # # flip the channel, since the original one using cv2
        # # rgb -> bgr
        # im = im[:, :, ::-1]
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]
        target_size = cfg.TRAIN.SCALES[scale_inds[i]]

        # TODO: color argumentation
        im = color_aug(im)

        im, im_scale = blob_utils.prep_im_for_blob(
            im, cfg.PIXEL_MEANS, [target_size], cfg.TRAIN.MAX_SIZE)
        im_scales.append(im_scale[0])
        processed_ims.append(im[0])

    # Create a blob to hold the input images [n, c, h, w]
    blob = blob_utils.im_list_to_blob(processed_ims)

    return blob, im_scales 

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import PIXEL_MEANS [as 别名]
def _get_image_blob(roidb):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    # Sample random scales to use for each image in this batch
    scale_inds = np.random.randint(
        0, high=len(cfg.TRAIN.SCALES), size=num_images
    )
    processed_ims = []
    im_scales = []
    for i in range(num_images):
        im = cv2.imread(roidb[i]['image'])
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]
        target_size = cfg.TRAIN.SCALES[scale_inds[i]]
        im, im_scale = blob_utils.prep_im_for_blob(
            im, cfg.PIXEL_MEANS, [target_size], cfg.TRAIN.MAX_SIZE
        )
        im_scales.append(im_scale[0])
        processed_ims.append(im[0])

    # Create a blob to hold the input images
    blob = blob_utils.im_list_to_blob(processed_ims)

    return blob, im_scales 

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import PIXEL_MEANS [as 别名]
def _get_image_blob(im):
    """Converts an image into a network input.

    Arguments:
        im (ndarray): a color image in BGR order

    Returns:
        blob (ndarray): a data blob holding an image pyramid
        im_scale_factors (list): list of image scales (relative to im) used
            in the image pyramid
    """
    im_orig = im.astype(np.float32, copy=True)
    im_orig -= cfg.PIXEL_MEANS

    im_shape = im_orig.shape
    im_size_min = np.min(im_shape[0:2])
    im_size_max = np.max(im_shape[0:2])

    processed_ims = []

    assert len(cfg.TEST.SCALES) == 1
    target_size = cfg.TEST.SCALES[0]

    im_scale = float(target_size) / float(im_size_min)
    # Prevent the biggest axis from being more than MAX_SIZE
    if np.round(im_scale * im_size_max) > cfg.TEST.MAX_SIZE:
        im_scale = float(cfg.TEST.MAX_SIZE) / float(im_size_max)
    im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale,
                    interpolation=cv2.INTER_LINEAR)
    im_info = np.hstack((im.shape[:2], im_scale))[np.newaxis, :]
    processed_ims.append(im)

    # Create a blob to hold the input images
    blob = im_list_to_blob(processed_ims)

    return blob, im_info 

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import PIXEL_MEANS [as 别名]
def _get_image_blob_from_images(roidb, images):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    # Sample random scales to use for each image in this batch
    scale_inds = np.random.randint(
        0, high=len(cfg.TRAIN.SCALES), size=num_images
    )
    processed_ims = []
    im_scales = []
    for i in range(num_images):
        im = images[i]
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]

        if cfg.TRAIN.USE_INVERSE and random.choice([True, False]):
            im = 255 - im

        target_size = cfg.TRAIN.SCALES[scale_inds[i]]
        im, im_scale = blob_utils.prep_im_for_blob(
            im, cfg.PIXEL_MEANS, [target_size], cfg.TRAIN.MAX_SIZE
        )
        im_scales.append(im_scale[0])
        processed_ims.append(im[0])

    # Create a blob to hold the input images
    blob = blob_utils.im_list_to_blob(processed_ims)

    return blob, im_scales 

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import PIXEL_MEANS [as 别名]
def _get_image_blob(roidb):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    # Sample random scales to use for each image in this batch
    scale_inds = np.random.randint(
        0, high=len(cfg.TRAIN.SCALES), size=num_images
    )
    processed_ims = []
    im_scales = []
    for i in range(num_images):
        im = cv2.imread(roidb[i]['image'])
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]

        if cfg.TRAIN.USE_INVERSE and random.choice([True, False]):
            im = 255 - im

        target_size = cfg.TRAIN.SCALES[scale_inds[i]]
        im, im_scale = blob_utils.prep_im_for_blob(
            im, cfg.PIXEL_MEANS, [target_size], cfg.TRAIN.MAX_SIZE
        )
        im_scales.append(im_scale[0])
        processed_ims.append(im[0])

    # Create a blob to hold the input images
    blob = blob_utils.im_list_to_blob(processed_ims)

    return blob, im_scales 

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import PIXEL_MEANS [as 别名]
def _get_image_blob(im_in):
    """Converts an image into a network input.

    Arguments:
        im (ndarray): a color image in BGR order

    Returns:
        blob (ndarray): a data blob holding an image pyramid
        im_scale_factors (list): list of image scales (relative to im) used
            in the image pyramid
    """
    im_orig = im_in.astype(np.float32, copy=True)
    im_orig -= cfg.PIXEL_MEANS

    im_shape = im_orig.shape
    im_size_min = np.min(im_shape[0:2])
    im_size_max = np.max(im_shape[0:2])

    if cfg.GRAY_IMAGES:
        im_orig = normalize_and_whiten(im_orig)

    processed_ims = []

    assert len(cfg.TEST.SCALES) == 1
    target_size = cfg.TEST.SCALES[0]

    im_scale = float(target_size) / float(im_size_min)
    # Prevent the biggest axis from being more than MAX_SIZE
    if np.round(im_scale * im_size_max) > cfg.TEST.MAX_SIZE:
        im_scale = float(cfg.TEST.MAX_SIZE) / float(im_size_max)
    im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale,
                    interpolation=cv2.INTER_LINEAR)
    im_info = np.hstack((im.shape[:2], im_scale))[np.newaxis, :]
    processed_ims.append(im)

    # Create a blob to hold the input images
    blob = im_list_to_blob(processed_ims)

    return blob, im_info