dataset_train.load_rice(FOOD_DIR, "train")
dataset_train.prepare()
# Validation dataset
dataset_val = RiceDataset()
dataset_val.load_rice(FOOD_DIR, "val")
dataset_val.prepare()
image, gt_class_ids, gt_boxes, gt_masks = mutils.load_image_gt(dataset_train, config, image_id=0, augment=None,
augmentation=None,
use_mini_mask=config.USE_MINI_MASK)
# image = image[:, :, ::-1]
# visualize.display_instances(image, gt_boxes, gt_masks, gt_class_ids, dataset_train.class_names)
# image = cv2.cvtColor(cv2.resize(image, (224, 224)), cv2.COLOR_BGR2RGB)
model = modellib.MaskYOLO(mode="inference",
config=config,
yolo_pretrain_dir=None,
yolo_trainable=True)
# print(model.keras_model.summary())
model.load_weights('./saved_model_Jan06-18-03.h5')
# model.infer_yolo(image, './yolo_model_Jan04-19-37.h5')
# model.train(dataset_train, dataset_val, learning_rate=config.LEARNING_RATE, epochs=20, layers='all')
# image = cv2.imread('./test.jpg')
# image = cv2.cvtColor(cv2.resize(image, (224, 224)), cv2.COLOR_BGR2RGB)
model.detect(image, './saved_model_Jan06-18-03.h5')
# file = open('./rice_boxes', 'w')
image, gt_class_ids, gt_boxes, gt_masks = mutils.load_image_gt(
dataset_train,
config,
image_id=0,
augment=None,
augmentation=None,
use_mini_mask=config.USE_MINI_MASK)
# file.write(str(gt_boxes[0]) + '\n')
# file.close()
# visualize.display_instances(image, gt_boxes, gt_masks, gt_class_ids, dataset_train.class_names)
image = cv2.cvtColor(cv2.resize(image, (224, 224)), cv2.COLOR_BGR2RGB)
image = image[:, :, ::-1]
model = modellib.MaskYOLO(mode="training",
config=config,
yolo_pretrain_dir=None,
yolo_trainable=True)
print(model.keras_model.summary())
# model.load_weights('./saved_model_Jan02-09-54.h5')
# model.infer_yolo(image, './saved_model_Jan01-21-14.h5')
# model.train(dataset_train, dataset_val, learning_rate=config.LEARNING_RATE, epochs=10, layers='all')
# image = cv2.imread('./test.jpg')
# image = cv2.cvtColor(cv2.resize(image, (224, 224)), cv2.COLOR_BGR2RGB)
model.detect(image, './saved_model_Jan02-10-04.h5')
# image, gt_class_ids, gt_boxes, gt_masks = mutils.load_image_gt(dataset_train, config, image_id=440, augment=None,
# augmentation=None,
# use_mini_mask=config.USE_MINI_MASK)
#
#
"""Return a Matplotlib Axes array to be used in
all visualizations in the notebook. Provide a
central point to control graph sizes.
Change the default size attribute to control the size
of rendered images
"""
_, ax = plt.subplots(rows, cols, figsize=(size * cols, size * rows))
return ax
inference_config = ShapesConfig()
inference_config.BATCH_SIZE = 1
inference_config.display()
''' Recreate the model in inference mode '''
model = modellib.MaskYOLO(mode="inference", config=inference_config)
''' Load trained weights '''
model.load_weights('./model_1216.h5', by_name=True)
''' Training dataset '''
dataset_train = ShapesDataset()
dataset_train.load_shapes(500, inference_config.IMAGE_SHAPE[0],
inference_config.IMAGE_SHAPE[1])
dataset_train.prepare()
''' Validation dataset '''
dataset_val = ShapesDataset()
dataset_val.load_shapes(50, inference_config.IMAGE_SHAPE[0],
inference_config.IMAGE_SHAPE[1])
dataset_val.prepare()
''' Test on a random image '''
image_id = random.choice(dataset_val.image_ids)
original_image, gt_class_id, gt_bbox, gt_mask = mutils.load_image_gt(
# boxes.append([y - s, x - s, y + s, x + s])
# Apply non-max suppression wit 0.3 threshold to avoid
# shapes covering each other
keep_ixs = utils.non_max_suppression(np.array(boxes), np.arange(N), 0.3)
shapes = [s for i, s in enumerate(shapes) if i in keep_ixs]
return bg_color, shapes
if __name__ == '__main__':
config = ShapesConfig()
config.display()
# Training dataset
dataset_train = ShapesDataset()
dataset_train.load_shapes(500, config.IMAGE_SHAPE[0], config.IMAGE_SHAPE[1])
dataset_train.prepare()
# Validation dataset
dataset_val = ShapesDataset()
dataset_val.load_shapes(50, config.IMAGE_SHAPE[0], config.IMAGE_SHAPE[1])
dataset_val.prepare()
image_ids = np.random.choice(dataset_train.image_ids, 4)
for image_id in image_ids:
image = dataset_train.load_image(image_id)
mask, class_ids = dataset_train.load_mask(image_id)
# visualize.display_top_masks(image, mask, class_ids, dataset_train.class_names)
box = extract_bboxes(mask)
model = modellib.MaskYOLO(mode="training", config=config)