Python blob.im_list_to_blob函数代码示例

    def __call__(self, sample):
        # resizes image and returns scale factors
        original_im_size=sample['image'].shape
        im_list,im_scales = prep_im_for_blob(sample['image'],
                                             pixel_means=self.mean,
                                             target_sizes=self.target_sizes,
                                             max_size=self.max_size)
        sample['image'] = torch.FloatTensor(im_list_to_blob(im_list,self.fpn_on)) # im_list_to blob swaps channels and adds stride in case of fpn
        sample['scaling_factors'] = im_scales[0] 
        sample['original_im_size'] = torch.FloatTensor(original_im_size)
        if len(sample['dbentry']['boxes'])!=0 and not self.sample_proposals_for_training: # Fast RCNN test
            proposals = sample['dbentry']['boxes']*im_scales[0]  
            if self.remove_dup_proposals:
                proposals,_ = self.remove_dup_prop(proposals) 
            
            if self.fpn_on==False:
                sample['rois'] = torch.FloatTensor(proposals)
            else:
                multiscale_proposals = add_multilevel_rois_for_test({'rois': proposals},'rois')
                for k in multiscale_proposals.keys():
                    sample[k] = torch.FloatTensor(multiscale_proposals[k])

        elif self.sample_proposals_for_training: # Fast RCNN training
            sampled_rois_labels_and_targets = fast_rcnn_sample_rois(roidb=sample['dbentry'],
                                                                    im_scale=im_scales[0],
                                                                    batch_idx=0) # ok as long as we keep batch_size=1
            sampled_rois_labels_and_targets = {key: torch.FloatTensor(value) for key,value in sampled_rois_labels_and_targets.items()}
            # add to sample
            sample = {**sample, **sampled_rois_labels_and_targets} 
        # remove dbentry from sample
        del sample['dbentry']
        return sample

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

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):
        if cfg.TRAIN.IS_COLOR == True:
            im = cv2.imread(roidb[i]['image'])
            if roidb[i]['flipped']:
                im = im[:, ::-1, :]
        else:
            im = cv2.imread(roidb[i]['image'], flags= cv2.CV_LOAD_IMAGE_GRAYSCALE)
            #im = cv2.cvtColor(gim, cv2.COLOR_GRAY2BGR)
            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

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

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_bgr = cv2.imread(roidb[i]['image'])
        if cfg.DEBUG:
	    print im_bgr.shape
	#******************************
        #   Add deformed mask to input
        #******************************
        deformed_mask = cv2.imread(roidb[i]['deformed_mask'],0)
        im = np.zeros((im_bgr.shape[0], im_bgr.shape[1], 4))
        im[:,:,0:3] = im_bgr
        im[:,:,3] = deformed_mask
        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

def _get_image_blob(im):
    """Converts an image into a network input.

    Arguments:
        im (list of ndarray): a list of color images in BGR order. In case of
        video it is a list of frames, else is is a list with len = 1.

    Returns:
        blob (ndarray): a data blob holding an image pyramid (or video pyramid)
        im_scale_factors (ndarray): array of image scales (relative to im) used
            in the image pyramid
    """
    all_processed_ims = []  # contains a a list for each frame, for each scale
    all_im_scale_factors = []
    for frame in im:
        processed_ims, im_scale_factors = blob_utils.prep_im_for_blob(
            frame, cfg.PIXEL_MEANS, cfg.TEST.SCALES, cfg.TEST.MAX_SIZE)
        all_processed_ims.append(processed_ims)
        all_im_scale_factors.append(im_scale_factors)
    # All the im_scale_factors will be the same, so just take the first one
    for el in all_im_scale_factors:
        assert(all_im_scale_factors[0] == el)
    im_scale_factors = all_im_scale_factors[0]
    # Now get all frames with corresponding scale next to each other
    processed_ims = []
    for i in range(len(all_processed_ims[0])):
        for frames_at_specific_scale in all_processed_ims:
            processed_ims.append(frames_at_specific_scale[i])
    # Now processed_ims contains
    # [frame1_scale1, frame2_scale1..., frame1_scale2, frame2_scale2...] etc
    blob = blob_utils.im_list_to_blob(processed_ims)
    return blob, np.array(im_scale_factors)

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

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'])
		#Multi channels supported
        im = np.load(roidb[i]['image'])
        if im.ndim != 3:
            im = np.expand_dims(im, axis=2)
        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

def _get_image_blob(roidb, scale_inds, data_i):
    """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):
        imname1 = roidb[i]["image"][data_i]
        imname2 = imname1 + "_norm.png"
        im1 = cv2.imread(imname1)
        im2 = cv2.imread(imname2)
        if roidb[i]["flipped"]:
            im1 = im1[:, ::-1, :]
            im2 = im2[:, ::-1, :]
            im2[:, :, 2] = 255 - im2[:, :, 2]

        im = np.zeros((im1.shape[0], im1.shape[1], 6))
        im = im.astype("uint8")
        im1 = im1[:, :, ::-1]
        im2 = im2[:, :, ::-1]
        im[:, :, 0:3] = im1
        im[:, :, 3:6] = im2

        target_size = cfg.TRAIN.SCALES[scale_inds[i]]
        im, im_scale = prep_im_for_blob(im, 127.5, 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

def _get_rprocessed_image_blob(roidb, scale_inds, angles):
    """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, :]
	
	if roidb[i]['rotated']:
	    # get the size of image
	    (h, w) = im.shape[:2] 
	    # set the rotation center
	    center = (w / 2, h / 2) 
	    # get the rotation matrix no scale changes
	    scale = 1.0
	    # anti-clockwise angle in the function
	    M = cv2.getRotationMatrix2D(center, angles[i], scale)
	    im = cv2.warpAffine(im,M,(w,h)) 
 
        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

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

    processed_ims = []

    assert len(cfg.TEST.SCALES_BASE) == 1
    im_scale = cfg.TRAIN.SCALES_BASE[0]

    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

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

    processed_ims = []
    im_scale_factors = []
    scales = cfg.TEST.SCALES_BASE

    for im_scale in scales:
        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)

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)

def _get_image_blob(imdb, 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):
        proto = imdb.get_proto_at(roidb[i]['image'])
        mem = BytesIO(proto.data)
        im = io.imread(mem)
        im = im[:,:,::-1]

        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, cfg.TRAIN.SCALE_MULTIPLE_OF)
        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

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):
        ims = image_utils.read_image_video(roidb[i])
        for im_id, im in enumerate(ims):
            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)
            ims[im_id] = im[0]
        # Just taking the im_scale for the last im in ims is fine (all are same)
        im_scales.append(im_scale[0])
        processed_ims += ims

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