def prep_oldshapes_train(init_with = None, FCN_layers = False, batch_sz = 5, epoch_steps = 4, training_folder= "mrcnn_oldshape_training_logs"):
import mrcnn.shapes as shapes
MODEL_DIR = os.path.join(TRAINING_DIR, training_folder)
# Build configuration object -----------------------------------------------
config = shapes.ShapesConfig()
config.BATCH_SIZE = batch_sz # Batch size is 2 (# GPUs * images/GPU).
config.IMAGES_PER_GPU = batch_sz # Must match BATCH_SIZE
config.STEPS_PER_EPOCH = epoch_steps
config.FCN_INPUT_SHAPE = config.IMAGE_SHAPE[0:2]
# Build shape dataset -----------------------------------------------
dataset_train = shapes.ShapesDataset(config)
dataset_train.load_shapes(3000)
dataset_train.prepare()
# Validation dataset
dataset_val = shapes.ShapesDataset(config)
dataset_val.load_shapes(500)
dataset_val.prepare()
try :
del model
print('delete model is successful')
gc.collect()
except:
pass
KB.clear_session()
model = modellib.MaskRCNN(mode="training", config=config, model_dir=MODEL_DIR, FCN_layers = FCN_layers)
print(' COCO Model Path : ', COCO_TRAINING_DIR)
print(' Checkpoint folder Path: ', MODEL_DIR)
print(' Model Parent Path : ', TRAINING_DIR)
print(' Resent Model Path : ', RESNET_TRAINING_DIR)
model.load_model_weights(init_with = init_with)
train_generator = data_generator(dataset_train, model.config, shuffle=True,
batch_size=model.config.BATCH_SIZE,
augment = False)
val_generator = data_generator(dataset_val, model.config, shuffle=True,
batch_size=model.config.BATCH_SIZE,
augment=False)
model.config.display()
return [model, dataset_train, dataset_val, train_generator, val_generator, config]
def prep_oldshapes_test(init_with = None, FCN_layers = False, batch_sz = 5, epoch_steps = 4, folder_name= "mrcnn_oldshape_test_logs"):
import mrcnn.shapes as shapes
MODEL_DIR = os.path.join(MODEL_PATH, folder_name)
# MODEL_DIR = os.path.join(MODEL_PATH, "mrcnn_development_logs")
# Build configuration object -----------------------------------------------
config = shapes.ShapesConfig()
config.BATCH_SIZE = batch_sz # Batch size is 2 (# GPUs * images/GPU).
config.IMAGES_PER_GPU = batch_sz # Must match BATCH_SIZE
config.STEPS_PER_EPOCH = epoch_steps
config.FCN_INPUT_SHAPE = config.IMAGE_SHAPE[0:2]
# Build shape dataset -----------------------------------------------
dataset_test = shapes.ShapesDataset()
dataset_test.load_shapes(500, config.IMAGE_SHAPE[0], config.IMAGE_SHAPE[1])
dataset_test.prepare()
# Recreate the model in inference mode
try :
del model
print('delete model is successful')
gc.collect()
except:
pass
KB.clear_session()
model = modellib.MaskRCNN(mode="inference",
config=config,
model_dir=MODEL_DIR,
FCN_layers = FCN_layers )
print(' COCO Model Path : ', COCO_MODEL_PATH)
print(' Checkpoint folder Path: ', MODEL_DIR)
print(' Model Parent Path : ', MODEL_PATH)
print(' Resent Model Path : ', RESNET_MODEL_PATH)
load_model(model, init_with = init_with)
test_generator = data_generator(dataset_test, model.config, shuffle=True,
batch_size=model.config.BATCH_SIZE,
augment = False)
model.config.display()
return [model, dataset_test, test_generator, config]
#-------------------------------------------------------------------------- # ## Dataset #-------------------------------------------------------------------------- # # Create a synthetic dataset # # Extend the Dataset class and add a method to load the shapes dataset, `load_shapes()`, and override the following methods: # # * load_image() # * load_mask() # * image_reference() # Training dataset # generate 500 shapes dataset_train = shapes.ShapesDataset() dataset_train.load_shapes(500, config.IMAGE_SHAPE[0], config.IMAGE_SHAPE[1]) dataset_train.prepare() # Validation dataset dataset_val = shapes.ShapesDataset() dataset_val.load_shapes(50, config.IMAGE_SHAPE[0], config.IMAGE_SHAPE[1]) dataset_val.prepare() # In[29]: #-------------------------------------------------------------------------- # Load and display random samples #-------------------------------------------------------------------------- # image_ids = np.random.choice(dataset_train.image_ids, 1) # for image_id in image_ids: