utils.py

from absl import logging
import numpy as np
import tensorflow as tf
import cv2

YOLOV3_LAYER_LIST = [
    'yolo_darknet',
    'yolo_conv_0',
    'yolo_output_0',
    'yolo_conv_1',
    'yolo_output_1',
    'yolo_conv_2',
    'yolo_output_2',
]


def load_darknet_weights(model, weights_file):
    wf = open(weights_file, 'rb')
    major, minor, revision, seen, _ = np.fromfile(wf, dtype=np.int32, count=5)

    for layer_name in YOLOV3_LAYER_LIST:
        sub_model = model.get_layer(layer_name)
        for i, layer in enumerate(sub_model.layers):
            if not layer.name.startswith('conv2d'):
                continue
            batch_norm = None
            if i + 1 < len(sub_model.layers) and \
                    sub_model.layers[i + 1].name.startswith('batch_norm'):
                batch_norm = sub_model.layers[i + 1]

            logging.info("{}/{} {}".format(
                sub_model.name, layer.name, 'bn' if batch_norm else 'bias'))

            filters = layer.filters
            size = layer.kernel_size[0]
            in_dim = layer.input_shape[-1]

            if batch_norm is None:
                conv_bias = np.fromfile(wf, dtype=np.float32, count=filters)
            else:
                # darknet [beta, gamma, mean, variance]
                bn_weights = np.fromfile(
                    wf, dtype=np.float32, count=4 * filters)
                # tf [gamma, beta, mean, variance]
                bn_weights = bn_weights.reshape((4, filters))[[1, 0, 2, 3]]

            # darknet shape (out_dim, in_dim, height, width)
            conv_shape = (filters, in_dim, size, size)
            conv_weights = np.fromfile(
                wf, dtype=np.float32, count=np.product(conv_shape))
            # tf shape (height, width, in_dim, out_dim)
            conv_weights = conv_weights.reshape(
                conv_shape).transpose([2, 3, 1, 0])

            if batch_norm is None:
                layer.set_weights([conv_weights, conv_bias])
            else:
                layer.set_weights([conv_weights])
                batch_norm.set_weights(bn_weights)

    assert len(wf.read()) == 0, 'failed to read all data'
    wf.close()


def broadcast_iou(box_1, box_2):
    # box_1: (..., (x1, y1, x2, y2))
    # box_2: (N, (x1, y1, x2, y2))

    # broadcast boxes
    box_1 = tf.expand_dims(box_1, -2)
    box_2 = tf.expand_dims(box_2, 0)
    # new_shape: (..., N, (x1, y1, x2, y2))
    new_shape = tf.broadcast_dynamic_shape(tf.shape(box_1), tf.shape(box_2))
    box_1 = tf.broadcast_to(box_1, new_shape)
    box_2 = tf.broadcast_to(box_2, new_shape)

    int_w = tf.maximum(tf.minimum(box_1[..., 2], box_2[..., 2]) -
                       tf.maximum(box_1[..., 0], box_2[..., 0]), 0)
    int_h = tf.maximum(tf.minimum(box_1[..., 3], box_2[..., 3]) -
                       tf.maximum(box_1[..., 1], box_2[..., 1]), 0)
    int_area = int_w * int_h
    box_1_area = (box_1[..., 2] - box_1[..., 0]) * \
        (box_1[..., 3] - box_1[..., 1])
    box_2_area = (box_2[..., 2] - box_2[..., 0]) * \
        (box_2[..., 3] - box_2[..., 1])
    return int_area / (box_1_area + box_2_area - int_area)


def draw_outputs(img, outputs, class_names):
    boxes, objectness, classes, nums = outputs
    boxes, objectness, classes, nums = boxes[0], objectness[0], classes[0], nums[0]
    wh = np.flip(img.shape[0:2])
    for i in range(nums):
        x1y1 = tuple((np.array(boxes[i][0:2]) * wh).astype(np.int32))
        x2y2 = tuple((np.array(boxes[i][2:4]) * wh).astype(np.int32))
        img = cv2.rectangle(img, x1y1, x2y2, (255, 0, 0), 2)
        img = cv2.putText(img, '{} {:.4f}'.format(
            class_names[int(classes[i])], objectness[i]),
            x1y1, cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 2)
    return img


def draw_labels(x, y, class_names):
    img = x.numpy()
    boxes, classes = tf.split(y, (4, 1), axis=-1)
    classes = classes[..., 0]
    wh = np.flip(img.shape[0:2])
    for i in range(len(boxes)):
        x1y1 = tuple((np.array(boxes[i][0:2]) * wh).astype(np.int32))
        x2y2 = tuple((np.array(boxes[i][2:4]) * wh).astype(np.int32))
        img = cv2.rectangle(img, x1y1, x2y2, (255, 0, 0), 2)
        img = cv2.putText(img, class_names[classes[i]],
                          x1y1, cv2.FONT_HERSHEY_COMPLEX_SMALL,
                          1, (0, 0, 255), 2)
    return img


def freeze_all(model, frozen=True):
    model.trainable = not frozen
    if isinstance(model, tf.keras.Model):
        for l in model.layers:
            freeze_all(l, frozen)
            
            
 ## Dataset utils ============
@tf.function
def transform_targets_for_output(y_true, grid_size, anchor_idxs, classes):
    # y_true: (N, boxes, (x1, y1, x2, y2, class, best_anchor))
    N = tf.shape(y_true)[0]

    # y_true_out: (N, grid, grid, anchors, [x, y, w, h, obj, class])
    y_true_out = tf.zeros(
        (N, grid_size, grid_size, tf.shape(anchor_idxs)[0], 6))

    anchor_idxs = tf.cast(anchor_idxs, tf.int32)

    indexes = tf.TensorArray(tf.int32, 1, dynamic_size=True)
    updates = tf.TensorArray(tf.float32, 1, dynamic_size=True)
    idx = 0
    for i in tf.range(N):
        for j in tf.range(tf.shape(y_true)[1]):
            if tf.equal(y_true[i][j][2], 0):
                continue
            anchor_eq = tf.equal(
                anchor_idxs, tf.cast(y_true[i][j][5], tf.int32))

            if tf.reduce_any(anchor_eq):
                box = y_true[i][j][0:4]
                box_xy = (y_true[i][j][0:2] + y_true[i][j][2:4]) / 2

                anchor_idx = tf.cast(tf.where(anchor_eq), tf.int32)
                grid_xy = tf.cast(box_xy // (1/grid_size), tf.int32)

                # grid[y][x][anchor] = (tx, ty, bw, bh, obj, class)
                indexes = indexes.write(
                    idx, [i, grid_xy[1], grid_xy[0], anchor_idx[0][0]])
                updates = updates.write(
                    idx, [box[0], box[1], box[2], box[3], 1, y_true[i][j][4]])
                idx += 1

    # tf.print(indexes.stack())
    # tf.print(updates.stack())

    return tf.tensor_scatter_nd_update(
        y_true_out, indexes.stack(), updates.stack())


def transform_targets(y_train, anchors, anchor_masks, classes):
    y_outs = []
    grid_size = 13

    # calculate anchor index for true boxes
    anchors = tf.cast(anchors, tf.float32)
    anchor_area = anchors[..., 0] * anchors[..., 1]
    box_wh = y_train[..., 2:4] - y_train[..., 0:2]
    box_wh = tf.tile(tf.expand_dims(box_wh, -2),
                     (1, 1, tf.shape(anchors)[0], 1))
    box_area = box_wh[..., 0] * box_wh[..., 1]
    intersection = tf.minimum(box_wh[..., 0], anchors[..., 0]) * \
        tf.minimum(box_wh[..., 1], anchors[..., 1])
    iou = intersection / (box_area + anchor_area - intersection)
    anchor_idx = tf.cast(tf.argmax(iou, axis=-1), tf.float32)
    anchor_idx = tf.expand_dims(anchor_idx, axis=-1)

    y_train = tf.concat([y_train, anchor_idx], axis=-1)

    for anchor_idxs in anchor_masks:
        y_outs.append(transform_targets_for_output(
            y_train, grid_size, anchor_idxs, classes))
        grid_size *= 2

    return tuple(y_outs)


def transform_images(x_train, size):
    x_train = tf.image.resize(x_train, (size, size))
    x_train = x_train / 255
    return x_train