def noise_label(labels):
id = range(shape(labels['click_position'])[0])
idx = concatenate(
[expand_dims(cast(id, int64), axis=1), labels['click_position']],
axis=1)
clicked_item = gather_nd(labels['reco'], idx)
return cast(equal(expand_dims(clicked_item, axis=1), labels['reco']),
float32)
def test_ficken(self):
labels = {'click_position': [1, 2], 'reco': [[0, 1, 2], [2, 1, 0]]}
id = range(shape(labels['click_position'])[0])
idx = concatenate([
expand_dims(cast(id, int64), axis=1),
expand_dims(cast(labels['click_position'], int64), axis=1)
],
axis=1)
clicked_item = gather_nd(labels['reco'], idx)
with self.test_session():
print(clicked_item.eval())
def create_label(click_position, num_labels=10):
num_rows = shape(click_position)[0]
row_idx = expand_dims(range(num_rows), axis=1)
idx = concatenate([row_idx, cast(click_position, int32)], axis=1)
labels = SparseTensor(indices=cast(idx, int64),
values=ones([num_rows]),
dense_shape=[num_rows, num_labels])
return ones([num_rows, num_labels]) - to_dense(labels)
def tf_iou(pred_xy: tf.Tensor, pred_wh: tf.Tensor, vaild_xy: tf.Tensor,
vaild_wh: tf.Tensor) -> tf.Tensor:
""" calc the iou form pred box with vaild box
Parameters
----------
pred_xy : tf.Tensor
pred box shape = [out h, out w, anchor num, 2]
pred_wh : tf.Tensor
pred box shape = [out h, out w, anchor num, 2]
vaild_xy : tf.Tensor
vaild box shape = [? , 2]
vaild_wh : tf.Tensor
vaild box shape = [? , 2]
Returns
-------
tf.Tensor
iou value shape = [out h, out w, anchor num ,?]
"""
b1_xy = tf.expand_dims(pred_xy, -2)
b1_wh = tf.expand_dims(pred_wh, -2)
b1_wh_half = b1_wh / 2.
b1_mins = b1_xy - b1_wh_half
b1_maxes = b1_xy + b1_wh_half
b2_xy = tf.expand_dims(vaild_xy, 0)
b2_wh = tf.expand_dims(vaild_wh, 0)
b2_wh_half = b2_wh / 2.
b2_mins = b2_xy - b2_wh_half
b2_maxes = b2_xy + b2_wh_half
intersect_mins = tf.maximum(b1_mins, b2_mins)
intersect_maxes = tf.minimum(b1_maxes, b2_maxes)
intersect_wh = tf.maximum(intersect_maxes - intersect_mins, 0.)
intersect_area = intersect_wh[..., 0] * intersect_wh[..., 1]
b1_area = b1_wh[..., 0] * b1_wh[..., 1]
b2_area = b2_wh[..., 0] * b2_wh[..., 1]
iou = intersect_area / (b1_area + b2_area - intersect_area)
return iou
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')
def create_diffs(positive_scores, scores):
return expand_dims(positive_scores, axis=1) - scores
def lookup_positives(scores, click_position):
num_rows = shape(scores)[0]
row_idx = expand_dims(range(num_rows), axis=1)
idx = concatenate([row_idx, cast(click_position, int32)], axis=1)
return gather_nd(scores, idx)
def predict_scores(features):
candidate = dense(features['label'], 10)
anchor = dense(features['anchor_label'], 10)
scores = matmul(candidate, expand_dims(anchor, axis=1), transpose_b=True)
return squeeze(scores)