config.display()
# Training dataset
dataset_train = ShapesDataset()
dataset_train.load_shapes(1000, config.IMAGE_SHAPE[0], config.IMAGE_SHAPE[1])
dataset_train.prepare()
# Validation dataset
dataset_val = ShapesDataset()
dataset_val.load_shapes(100, config.IMAGE_SHAPE[0], config.IMAGE_SHAPE[1])
dataset_val.prepare()
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)
# config.BATCH_SIZE = 1
model = modellib.MaskYOLO(mode="training",
config=config,
yolo_pretrain_dir=None,
yolo_trainable=True)
model.load_weights('./saved_model_Dec27-14-43.h5')
# model.detect(image, './saved_model_Dec27-14-43.h5')
model.train(dataset_train,
dataset_val,
learning_rate=config.LEARNING_RATE,
dataset_val = RiceDataset()
dataset_val.load_rice(RICE_DIR, "val")
dataset_val.prepare()
# all_info = []
# for id in range(0, 500):
# image, gt_class_ids, gt_boxes, gt_masks = \
# mutils.load_image_gt(dataset_train, config, id,
# use_mini_mask=config.USE_MINI_MASK)
# all_info.append([image, gt_class_ids, gt_boxes, gt_masks])
# Data generators
train_info = []
for id in range(0, 53):
image, gt_class_ids, gt_boxes, gt_masks = \
mutils.load_image_gt(dataset_train, config, id,
use_mini_mask=config.USE_MINI_MASK)
train_info.append([image, gt_class_ids, gt_boxes, gt_masks])
val_info = []
for id in range(0, 6):
image, gt_class_ids, gt_boxes, gt_masks = \
mutils.load_image_gt(dataset_val, config, id,
use_mini_mask=config.USE_MINI_MASK)
val_info.append([image, gt_class_ids, gt_boxes, gt_masks])
train_generator = mutils.BatchGenerator(train_info,
config,
mode='training',
shuffle=True,
jitter=False,
norm=True)
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(
dataset_val, inference_config, image_id, use_mini_mask=False)
# visualize.display_instances(original_image, gt_bbox, gt_mask, gt_class_id,
# dataset_train.class_names, figsize=(8, 8))
results = model.detect_for_one([original_image], verbose=1)
r = results[0]
print(r)
# visualize.display_instances(original_image, r['rois'], r['masks'], r['class_ids'],
# dataset_val.class_names, r['scores'], ax=get_ax())