Python blob.im_list_to_blob方法代码示例

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [as 别名]
def _get_image_blob(roidb, scale_inds):
  """Builds an input blob from the images in the roidb at the specified
  scales.
  """
  num_images = len(roidb)
  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 = 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 = im_list_to_blob(processed_ims)

  return blob, im_scales 

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [as 别名]
def _get_image_blob(roidb, scale_inds):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    processed_ims = []
    im_scales = []
    for i in range(num_images):
        im = helper.read_rgb_img(roidb[i]['image'])
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]
        target_size = cfg.TRAIN.SCALES[scale_inds[i]]
        im, im_scale = 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 = im_list_to_blob(processed_ims)

    return blob, im_scales 

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [as 别名]
def _get_image_blob(roidb, scale_inds):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    processed_ims = []
    im_scales = []
    im_shapes = np.zeros((0, 2), dtype=np.float32)
    for i in xrange(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, im_shape = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size)
        im_scales.append(im_scale)
        processed_ims.append(im)
        im_shapes = np.vstack((im_shapes, im_shape))

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

    return blob, im_scales, im_shapes 

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [as 别名]
def _get_image_blob(roidb, scale_inds):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    processed_ims = []
    im_scales = []
    for i in xrange(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 = 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 = im_list_to_blob(processed_ims)

    return blob, im_scales 

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [as 别名]
def _get_image_blob(roidb, scale_inds):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    processed_ims = []
    im_scales = []
    for i in xrange(num_images):
        im = roidb[i]['image']() # use image getter

        if roidb[i]['flipped']:
            im = im[:, ::-1, :]
        target_size = cfg.TRAIN.SCALES[scale_inds[i]]
        im, im_scale = 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 = im_list_to_blob(processed_ims)

    return blob, im_scales 

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [as 别名]
def _get_image_blob(roidb, scale_inds):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    processed_ims = []
    im_scales = []
    for i in xrange(num_images):
        im = cv2.imread(roidb[i]['image'])
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]

        im_orig = im.astype(np.float32, copy=True)
        im_orig -= cfg.PIXEL_MEANS

        im_scale = cfg.TRAIN.SCALES_BASE[scale_inds[i]]
        im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)

        im_scales.append(im_scale)
        processed_ims.append(im)

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

    return blob, im_scales 

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [as 别名]
def _get_image_blob_multiscale(roidb):
    """Builds an input blob from the images in the roidb at multiscales.
    """
    num_images = len(roidb)
    processed_ims = []
    im_scales = []
    scales = cfg.TRAIN.SCALES_BASE
    for i in xrange(num_images):
        im = cv2.imread(roidb[i]['image'])
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]

        im_orig = im.astype(np.float32, copy=True)
        im_orig -= cfg.PIXEL_MEANS

        for im_scale in scales:
            im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
            im_scales.append(im_scale)
            processed_ims.append(im)

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

    return blob, im_scales 

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [as 别名]
def get_image_blob(roidb, scale_inds, scales, max_scale):
  """Builds an input blob from the images in the roidb at the specified
  scales.
  """
  num_images = len(roidb)
  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 = scales[scale_inds[i]]
    im, im_scale = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size,
                    max_scale)
    im_scales.append(im_scale)
    processed_ims.append(im)

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

  return blob, im_scales 

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [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 utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [as 别名]
def _get_image_blob(roidb, scale_inds):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    processed_ims = []
    im_scales = []
    im_shapes = np.zeros((0, 2), dtype=np.float32)
    for i in xrange(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, im_shape = prep_im_for_blob(im, cfg.PIXEL_MEANS, 
                                                  target_size, 
                                                  cfg.TRAIN.MAX_SIZE)
        im_scales.append(im_scale)
        processed_ims.append(im)
        im_shapes = np.vstack((im_shapes, im_shape))

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

    return blob, im_scales, im_shapes 

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [as 别名]
def _get_image_blob(roidb, scale_inds):
  """Builds an input blob from the images in the roidb at the specified
  scales.
  """
  num_images = len(roidb)
  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 = 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 = im_list_to_blob(processed_ims)

  return blob, im_scales 

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [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 = []
  im_scale_factors = []

  for target_size in cfg.TEST.SCALES:
    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_scale_factors.append(im_scale)
    processed_ims.append(im)

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

  return blob, np.array(im_scale_factors) 

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [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 = []
    im_scale_factors = []

    for target_size in cfg.TEST.SCALES:
        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_scale_factors.append(im_scale)
        processed_ims.append(im)

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

    return blob, np.array(im_scale_factors) 

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [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])
    # print(">>>>>>>>", im_shape[0], im_shape[1])

    processed_ims = []
    im_scale_factors = []

    for target_size in cfg.TEST.SCALES:
        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_scale_factors.append(im_scale)
        processed_ims.append(im)

    # Create a blob to hold the input images
    print(">>>>>>>>", im.shape[0], im.shape[1])
    blob = im_list_to_blob(processed_ims)

    return blob, np.array(im_scale_factors) 

# 需要导入模块: from utils import blob [as 别名]
# 或者: from utils.blob import im_list_to_blob [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