image, boxes = crop(image, boxes, prob=self.crop_prob)
image, boxes = translate(image, boxes, prob=self.translate_prob)
return image, boxes
if __name__ == '__main__':
from generators.pascal import PascalVocGenerator
train_generator = PascalVocGenerator('datasets/VOC0712',
'trainval',
skip_difficult=True,
anchors_path='voc_anchors_416.txt',
batch_size=1)
misc_effect = MiscEffect()
for i in range(train_generator.size()):
image = train_generator.load_image(i)
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
annotations = train_generator.load_annotations(i)
boxes = annotations['bboxes']
for box in boxes.astype(np.int32):
cv2.rectangle(image, (box[0], box[1]), (box[2], box[3]),
(0, 0, 255), 2)
src_image = image.copy()
cv2.namedWindow('src_image', cv2.WINDOW_NORMAL)
cv2.imshow('src_image', src_image)
image, boxes = misc_effect(image, boxes)
for box in boxes.astype(np.int32):
cv2.rectangle(image, (box[0], box[1]), (box[2], box[3]),
(0, 255, 0), 1)
cv2.namedWindow('image', cv2.WINDOW_NORMAL)
cv2.imshow('image', image)
def main():
generator = PascalVocGenerator(cfg.IMAGE_DIR,
cfg.ANNOTATION_DIR,
cfg.TEST_TEXT,
classes=cfg.CLASSES,
skip_difficult=True,
train_data=False)
num_classes = generator.num_classes()
classes = list(generator.classes.keys())
colors = [
np.random.randint(0, 256, 3).tolist() for i in range(num_classes)
]
model = centernet(num_classes,
score_threshold=cfg.SCORE_THRESHOLD,
nms=cfg.NMS,
flip_test=cfg.FLIP_TEST,
training=False)
model.load_weights(model_path, by_name=True, skip_mismatch=True)
for i in range(10):
image = generator.load_image(i)
#cv2.imwrite("./results/{}_o.jpg".format(i), image)
src_image = image.copy()
c = np.array([image.shape[1] / 2., image.shape[0] / 2.],
dtype=np.float32)
s = max(image.shape[0], image.shape[1]) * 1.0
tgt_w = generator.input_size
tgt_h = generator.input_size
image = generator.preprocess_image(image,
c,
s,
tgt_w=tgt_w,
tgt_h=tgt_h)
if cfg.FLIP_TEST:
flipped_image = image[:, ::-1]
inputs = np.stack([image, flipped_image], axis=0)
else:
inputs = np.expand_dims(image, axis=0)
detections = model.predict_on_batch(inputs)[0]
scores = detections[:, 4]
indices = np.where(scores > cfg.SCORE_THRESHOLD)[0]
detections = detections[indices]
detections_copy = detections.copy()
detections = detections.astype(np.float64)
trans = get_affine_transform(c, s, (tgt_w // 4, tgt_h // 4), inv=1)
for j in range(detections.shape[0]):
detections[j, 0:2] = affine_transform(detections[j, 0:2], trans)
detections[j, 2:4] = affine_transform(detections[j, 2:4], trans)
detections[:, [0, 2]] = np.clip(detections[:, [0, 2]], 0,
src_image.shape[1])
detections[:, [1, 3]] = np.clip(detections[:, [1, 3]], 0,
src_image.shape[0])
for detection in detections:
xmin = int(round(detection[0]))
ymin = int(round(detection[1]))
xmax = int(round(detection[2]))
ymax = int(round(detection[3]))
score = '{:.4f}'.format(detection[4])
class_id = int(detection[5])
color = colors[class_id]
class_name = classes[class_id]
label = '-'.join([class_name, score])
ret, baseline = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX,
0.5, 1)
cv2.rectangle(src_image, (xmin, ymin), (xmax, ymax), color, 1)
cv2.rectangle(src_image, (xmin, ymax - ret[1] - baseline),
(xmin + ret[0], ymax), color, -1)
cv2.putText(src_image, label, (xmin, ymax - baseline),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 1)
#cv2.imwrite("./results/{}_r.jpg".format(i), src_image)
cv2.imshow('image', src_image)
cv2.waitKey(0)
num_classes = generator.num_classes()
classes = list(generator.classes.keys())
flip_test = True
nms = True
keep_resolution = False
score_threshold = 0.1
colors = [np.random.randint(0, 256, 3).tolist() for i in range(num_classes)]
model, prediction_model, debug_model = centernet(
num_classes=num_classes,
nms=nms,
flip_test=flip_test,
freeze_bn=True,
score_threshold=score_threshold)
prediction_model.load_weights(model_path, by_name=True, skip_mismatch=True)
for i in range(10):
image = generator.load_image(i)
src_image = image.copy()
c = np.array([image.shape[1] / 2., image.shape[0] / 2.], dtype=np.float32)
s = max(image.shape[0], image.shape[1]) * 1.0
tgt_w = generator.input_size
tgt_h = generator.input_size
image = generator.preprocess_image(image, c, s, tgt_w=tgt_w, tgt_h=tgt_h)
if flip_test:
flipped_image = image[:, ::-1]
inputs = np.stack([image, flipped_image], axis=0)
else:
inputs = np.expand_dims(image, axis=0)
# run network
start = time.time()