def correct_box(box_xy: tf.Tensor, box_wh: tf.Tensor, input_shape: list,
image_shape: list) -> tf.Tensor:
"""rescae predict box to orginal image scale
Parameters
----------
box_xy : tf.Tensor
box xy
box_wh : tf.Tensor
box wh
input_shape : list
input shape
image_shape : list
image shape
Returns
-------
tf.Tensor
new boxes
"""
box_yx = box_xy[..., ::-1]
box_hw = box_wh[..., ::-1]
input_shape = tf.cast(input_shape, tf.float32)
image_shape = tf.cast(image_shape, tf.float32)
new_shape = tf.round(image_shape *
tf.reduce_min(input_shape / image_shape))
offset = (input_shape - new_shape) / 2. / input_shape
scale = input_shape / new_shape
box_yx = (box_yx - offset) * scale
box_hw *= scale
box_mins = box_yx - (box_hw / 2.)
box_maxes = box_yx + (box_hw / 2.)
boxes = tf.concat(
[
box_mins[..., 0:1], # y_min
box_mins[..., 1:2], # x_min
box_maxes[..., 0:1], # y_max
box_maxes[..., 1:2] # x_max
],
axis=-1)
# Scale boxes back to original image shape.
boxes *= tf.concat([image_shape, image_shape], axis=-1)
return boxes
def _process_img(self, img: np.ndarray, true_box: np.ndarray,
is_training: bool, is_resize: bool) -> tuple:
""" process image and true box , if is training then use data augmenter
Parameters
----------
img : np.ndarray
image srs
true_box : np.ndarray
box
is_training : bool
wether to use data augmenter
is_resize : bool
wether to resize the image
Returns
-------
tuple
image src , true box
"""
if is_resize:
""" resize image and keep ratio """
img_wh = np.array([img.shape[1], img.shape[0]])
in_wh = self.in_hw[0][::-1]
""" calculate the affine transform factor """
scale = in_wh / img_wh # NOTE affine tranform sacle is [w,h]
scale[:] = np.min(scale)
# NOTE translation is [w offset,h offset]
translation = ((in_wh - img_wh * scale) / 2).astype(int)
""" calculate the box transform matrix """
if isinstance(true_box, np.ndarray):
true_box[:, 1:3] = (true_box[:, 1:3] * img_wh * scale +
translation) / in_wh
true_box[:, 3:5] = (true_box[:, 3:5] * img_wh * scale) / in_wh
elif isinstance(true_box, tf.Tensor):
# NOTE use concat replace item assign
true_box = tf.concat(
(true_box[:, 0:1],
(true_box[:, 1:3] * img_wh * scale + translation) / in_wh,
(true_box[:, 3:5] * img_wh * scale) / in_wh),
axis=1)
""" apply Affine Transform """
aff = skimage.transform.AffineTransform(scale=scale,
translation=translation)
img = skimage.transform.warp(img,
aff.inverse,
output_shape=self.in_hw[0],
preserve_range=True).astype('uint8')
if is_training:
img, true_box = self.data_augmenter(img, true_box)
# normlize image
img = img / np.max(img)
return img, true_box
def main(ckpt_weights, image_size, output_size, model_def, class_num,
depth_multiplier, obj_thresh, iou_thresh, train_set, test_image):
h = Helper(None, class_num, f'data/{train_set}_anchor.npy',
np.reshape(np.array(image_size), (-1, 2)),
np.reshape(np.array(output_size), (-1, 2)))
network = eval(model_def) # type :yolo_mobilev2
yolo_model, yolo_model_warpper = network([image_size[0], image_size[1], 3],
len(h.anchors[0]),
class_num,
alpha=depth_multiplier)
yolo_model_warpper.load_weights(str(ckpt_weights))
print(INFO, f' Load CKPT {str(ckpt_weights)}')
orig_img = h._read_img(str(test_image))
image_shape = orig_img.shape[0:2]
img, _ = h._process_img(orig_img,
true_box=None,
is_training=False,
is_resize=True)
""" load images """
img = tf.expand_dims(img, 0)
y_pred = yolo_model_warpper.predict(img)
""" box list """
_yxyx_box = []
_yxyx_box_scores = []
""" preprocess label """
for l, pred_label in enumerate(y_pred):
""" split the label """
pred_xy = pred_label[..., 0:2]
pred_wh = pred_label[..., 2:4]
pred_confidence = pred_label[..., 4:5]
pred_cls = pred_label[..., 5:]
# box_scores = obj_score * class_score
box_scores = tf.sigmoid(pred_cls) * tf.sigmoid(pred_confidence)
# obj_mask = pred_confidence_score[..., 0] > obj_thresh
""" reshape box """
# NOTE tf_xywh_to_all will auto use sigmoid function
pred_xy_A, pred_wh_A = tf_xywh_to_all(pred_xy, pred_wh, l, h)
boxes = correct_box(pred_xy_A, pred_wh_A, image_size, image_shape)
boxes = tf.reshape(boxes, (-1, 4))
box_scores = tf.reshape(box_scores, (-1, class_num))
""" append box and scores to global list """
_yxyx_box.append(boxes)
_yxyx_box_scores.append(box_scores)
yxyx_box = tf.concat(_yxyx_box, axis=0)
yxyx_box_scores = tf.concat(_yxyx_box_scores, axis=0)
mask = yxyx_box_scores >= obj_thresh
""" do nms for every classes"""
_boxes = []
_scores = []
_classes = []
for c in range(class_num):
class_boxes = tf.boolean_mask(yxyx_box, mask[:, c])
class_box_scores = tf.boolean_mask(yxyx_box_scores[:, c], mask[:, c])
select = tf.image.non_max_suppression(class_boxes,
scores=class_box_scores,
max_output_size=30,
iou_threshold=iou_thresh)
class_boxes = tf.gather(class_boxes, select)
class_box_scores = tf.gather(class_box_scores, select)
_boxes.append(class_boxes)
_scores.append(class_box_scores)
_classes.append(tf.ones_like(class_box_scores) * c)
boxes = tf.concat(_boxes, axis=0)
classes = tf.concat(_classes, axis=0)
scores = tf.concat(_scores, axis=0)
""" draw box """
font = ImageFont.truetype(font='asset/FiraMono-Medium.otf',
size=tf.cast(
tf.floor(3e-2 * image_shape[0] + 0.5),
tf.int32).numpy())
thickness = (image_shape[0] + image_shape[1]) // 300
""" show result """
if len(classes) > 0:
pil_img = Image.fromarray(orig_img)
print(f'[top\tleft\tbottom\tright\tscore\tclass]')
for i, c in enumerate(classes):
box = boxes[i]
score = scores[i]
label = '{:2d} {:.2f}'.format(int(c.numpy()), score.numpy())
draw = ImageDraw.Draw(pil_img)
label_size = draw.textsize(label, font)
top, left, bottom, right = box
print(
f'[{top:.1f}\t{left:.1f}\t{bottom:.1f}\t{right:.1f}\t{score:.2f}\t{int(c):2d}]'
)
top = max(0, tf.cast(tf.floor(top + 0.5), tf.int32))
left = max(0, tf.cast(tf.floor(left + 0.5), tf.int32))
bottom = min(image_shape[0],
tf.cast(tf.floor(bottom + 0.5), tf.int32))
right = min(image_shape[1], tf.cast(tf.floor(right + 0.5),
tf.int32))
if top - image_shape[0] >= 0:
text_origin = tf.convert_to_tensor([left, top - label_size[1]])
else:
text_origin = tf.convert_to_tensor([left, top + 1])
for j in range(thickness):
draw.rectangle([left + j, top + j, right - j, bottom - j],
outline=h.colormap[c])
draw.rectangle(
[tuple(text_origin),
tuple(text_origin + label_size)],
fill=h.colormap[c])
draw.text(text_origin, label, fill=(0, 0, 0), font=font)
del draw
pil_img.show()
else:
print(NOTE, ' no boxes detected')
