def transform(example, output_size=(HEIGHT, WIDTH), training=True): image, objects, image_id = decode(example) # if training: # image = random_resize(image, output_size, ratio_range=(0.8, 1.2)) # image, objects = random_crop(image, objects, output_size) # image, objects = random_hflip(image, objects, 0.5) # else: image = resize(image, output_size) image = normalize(image, [123.68, 116.779, 103.939], [58.393, 57.12, 57.375]) image, objects = pad_to(image, objects, output_size) gt_bboxes, gt_labels = get(['gt_bbox', 'gt_label'], objects) gt_bboxes = coords_to_absolute(gt_bboxes, tf.shape(image)[:2]) bbox_targets, labels = atss_match(gt_bboxes, gt_labels, anchors, num_level_bboxes, topk=9, centerness=False) return image, { 'bbox_target': bbox_targets, 'label': labels, 'image_id': image_id }
def preprocess(example, output_size=(HEIGHT, WIDTH), max_objects=50, training=True): image, objects, image_id = decode(example) if training: image = random_resize(image, output_size, ratio_range=(0.5, 2.0)) image, objects = random_crop(image, objects, output_size) image, objects = random_hflip(image, objects, 0.5) else: image = resize(image, output_size) image = normalize(image, [123.68, 116.779, 103.939], [58.393, 57.12, 57.375]) image, objects = pad_to(image, objects, output_size) gt_bboxes, gt_labels = get(['gt_bbox', 'gt_label'], objects) gt_bboxes = coords_to_absolute(gt_bboxes, tf.shape(image)[:2]) objects = {**objects, 'gt_bbox': gt_bboxes} bbox_targets, labels, centerness = atss_match( gt_bboxes, gt_labels, anchors, num_level_bboxes, topk=9, centerness=True) objects = pad_objects(objects, max_objects) image = tf.cast(image, tf.bfloat16) return image, {'bbox_target': bbox_targets, 'label': labels, 'centerness': centerness, **objects, 'image_id': image_id}
def preprocess(example, output_size=(HEIGHT, WIDTH), max_objects=50, training=True): image, objects, image_id = decode(example) # if training: # image = random_resize(image, output_size, ratio_range=(0.8, 1.2)) # image, objects = random_crop(image, objects, output_size) # image, objects = random_hflip(image, objects, 0.5) # else: image = resize(image, output_size) image = normalize(image, [123.68, 116.779, 103.939], [58.393, 57.12, 57.375]) image, objects = pad_to(image, objects, output_size) gt_bboxes, gt_labels = get(['gt_bbox', 'gt_label'], objects) gt_bboxes = coords_to_absolute(gt_bboxes, tf.shape(image)[:2]) objects = {**objects, 'gt_bbox': gt_bboxes} bbox_targets, labels, ignore = max_iou_match(gt_bboxes, gt_labels, bbox_coder, pos_iou_thr=0.5, neg_iou_thr=0.4) objects = pad_objects(objects, max_objects) return image, { 'bbox_target': bbox_targets, 'label': labels, 'ignore': ignore, **objects, 'image_id': image_id }
def transform(image, label, training): image = pad(image, 2) image, label = to_tensor(image, label) image = normalize(image, [0.1307], [0.3081]) label = tf.one_hot(label, 10) return image, label
def transform(image, label, training): if training: image = random_crop(image, (32, 32), (4, 4)) image = tf.image.random_flip_left_right(image) image, label = to_tensor(image, label) image = normalize(image, [0.491, 0.482, 0.447], [0.247, 0.243, 0.262]) label = tf.one_hot(label, 100) return image, label
def transform(image, label, training): if training: image = random_crop(image, (32, 32), (4, 4)) image = tf.image.random_flip_left_right(image) image = autoaugment(image, "CIFAR10") image, label = to_tensor(image, label) image = normalize(image, [0.491, 0.482, 0.447], [0.247, 0.243, 0.262]) if training: image = random_apply(cutout(length=16), params['cutout_prob'], image) label = tf.one_hot(label, 100) return image, label
def transform(image, label, training): if training: image = random_crop(image, (32, 32), (4, 4)) image = tf.image.random_flip_left_right(image) # image = autoaugment(image, "CIFAR10") image, label = to_tensor(image, label) image = normalize(image, [0.491, 0.482, 0.447], [0.247, 0.243, 0.262]) # if training: # image = cutout(image, 16) label = tf.one_hot(label, 10) return image, label
def transform(image, label, training): if training: image = random_resized_crop(image, 160, scale=(0.05, 1.0), ratio=(0.75, 1.33)) image = tf.image.random_flip_left_right(image) else: image = resize(image, int(256 / 224 * 224)) image = center_crop(image, 224) image, label = to_tensor(image, label, label_offset=1) image = normalize(image, [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) label = tf.one_hot(label, 1000) return image, label
def preprocess(example, output_size=(HEIGHT, WIDTH), max_objects=50, training=True): image, objects, image_id = decode(example) # if training: # image = random_resize(image, output_size, ratio_range=(0.8, 1.2)) # image, objects = random_crop(image, objects, output_size) # image, objects = random_hflip(image, objects, 0.5) # else: image = resize(image, output_size) image = normalize(image, [123.68, 116.779, 103.939], [58.393, 57.12, 57.375]) image, objects = pad_to(image, objects, output_size) gt_bboxes, gt_labels, is_difficults = get( ['bbox', 'label', 'is_difficult'], objects) gt_bboxes = coords_to_absolute(gt_bboxes, tf.shape(image)[:2]) assigned_gt_inds = atss_assign(anchors, num_level_bboxes, gt_bboxes, topk=9) bbox_targets, labels, centerness, ignore = encode_target(gt_bboxes, gt_labels, assigned_gt_inds, bbox_coder, encode_bbox=False, centerness=True) gt_bboxes = pad_to_fixed_size(gt_bboxes, max_objects) gt_labels = pad_to_fixed_size(gt_labels, max_objects) is_difficults = pad_to_fixed_size(is_difficults, max_objects) # image = tf.cast(image, tf.bfloat16) return image, { 'bbox_target': bbox_targets, 'label': labels, 'ignore': ignore, 'centerness': centerness, 'gt_bbox': gt_bboxes, 'gt_label': gt_labels, 'is_difficult': is_difficults, 'image_id': image_id }
def preprocess(example, output_size=(HEIGHT, WIDTH), max_objects=50, training=True): image, objects, image_id = decode(example) # if training: # image = random_resize(image, output_size, ratio_range=(0.8, 1.2)) # image, objects = random_crop(image, objects, output_size) # image, objects = random_hflip(image, objects, 0.5) # else: image = resize(image, output_size) image = normalize(image, [123.68, 116.779, 103.939], [58.393, 57.12, 57.375]) image, objects = pad_to(image, objects, output_size) gt_bboxes, gt_labels = get(['gt_bbox', 'gt_label'], objects) gt_bboxes = coords_to_absolute(gt_bboxes, tf.shape(image)[:2]) objects = {**objects, 'gt_bbox': gt_bboxes} bbox_targets, labels, centerness = fcos_match(gt_bboxes, gt_labels, points, num_level_points, strides=strides, radius=0.5) objects = pad_objects(objects, max_objects) return image, { 'bbox_target': bbox_targets, 'label': labels, 'centerness': centerness, **objects, 'image_id': image_id }
def transform(x, y, training): x, y = to_tensor(x, y, vmax=16) x = normalize(x, [4.8842], [6.0168]) return x, y
skip_prefetch=True)) it = iter(ds_train) example = next(it) image, objects, image_id = decode(example) # if training: # image = random_resize(image, output_size, ratio_range=(0.8, 1.2)) # image, objects = random_crop(image, objects, output_size) # image, objects = random_hflip(image, objects, 0.5) # else: image = resize(image, output_size) image = normalize(image, [123.68, 116.779, 103.939], [58.393, 57.12, 57.375]) image, objects = pad_to(image, objects, output_size) gt_bboxes, gt_labels = get(['gt_bbox', 'gt_label'], objects) gt_bboxes = coords_to_absolute(gt_bboxes, tf.shape(image)[:2]) objects = {**objects, 'gt_bbox': gt_bboxes} bbox_targets, labels, centerness = atss_match(gt_bboxes, gt_labels, anchors, num_level_bboxes, topk=9, centerness=True) objects = pad_objects(objects, max_objects)