def create_histogrames(path=None): log_path = data_functions.create_path(LOG_PATH, 'extract_logs') configure_logger(name="stem_extractor", console_level='INFO', file_level='INFO', out_path=log_path) logger = logging.getLogger(__name__) try: params_dict = data_functions.load_json(path) stem_extract.create_test_train_obj(**params_dict) except: message = 'Error loading Model' logger.exception(message) raise Exception
def train_unet(params_dict_path, src_path, update_dict_path, steps): log_path = data_functions.create_path(LOG_PATH, 'unet_logs') configure_logger(name="cherry_stem", console_level='INFO', file_level='INFO', out_path=log_path) logger = logging.getLogger(__name__) try: if params_dict_path is not None: if src_path is not None: message = 'Ambiguous loading paths, input either' \ ' "params_dict_path or "src_path", not both ' raise UnetModelException(message) else: params_dict = data_functions.load_json(params_dict_path) model = unet_model_functions.ClarifruitUnet(**params_dict) else: if update_dict_path is not None: update_dict = data_functions.load_json(update_dict_path) else: update_dict = None model = unet_model_functions.ClarifruitUnet.load_model( src_path, update_dict, steps) keras_logs_path = model.set_model_for_train() logger.info(f"for tensorboard use \n " f"tensorboard --logdir={keras_logs_path}") model.fit_unet() except: message = 'Error loading Model' logger.exception(message) raise Exception
import os from work.unet import unet_model_functions from keras.callbacks import ReduceLROnPlateau from work.auxiliary import data_functions from work.auxiliary.logger_settings import configure_logger import logging LOG_PATH = os.path.abspath('logs') DATA_PATH = os.path.abspath('data') log_path = data_functions.create_path(LOG_PATH, 'unet_logs') configure_logger(name="cherry_stem", console_level='INFO', file_level='INFO', out_path=log_path) logger = logging.getLogger(__name__) def main(): """ for model debugging :return: """ # train_path = os.path.join(DATA_PATH, r'raw_data\with_maskes') #train_path = os.path.join(DATA_PATH, r'segmentation\augmented') train_path = os.path.join(DATA_PATH, r'segmentation\augmented') dest_path = os.path.join(DATA_PATH, r'unet_data\training')
from work.stem_classifier import classify from work.auxiliary import data_functions import os from work.stem_classifier.model_functions import * from work.auxiliary.logger_settings import configure_logger LOG_PATH = os.path.abspath('logs') DATA_PATH = os.path.abspath('data') log_path = data_functions.create_path(LOG_PATH, 'classifier') configure_logger(name="classifier", console_level='INFO', file_level='INFO', out_path=log_path) logger = logging.getLogger(__name__) def func(): train_path = r'D:\Clarifruit\cherry_stem\data\classification_data\from_all\set1\train' dest_path = r'D:\Clarifruit\cherry_stem\data\unet_data\training\2019-10-07_20-12-39' test_path = r'D:\Clarifruit\cherry_stem\data\classification_data\from_all\set1\test' params_dict = dict(train_path=train_path, data_gen_args=dict(rescale=1. / 255, rotation_range=180, width_shift_range=0.25, height_shift_range=0.25, shear_range=0.2, zoom_range=[0.5, 1.0],
from work.auxiliary import data_functions import cv2 from work.segmentation import segmentation import os from work.auxiliary.logger_settings import configure_logger import logging LOG_PATH = os.path.abspath('logs') DATA_PATH = os.path.abspath('data') log_path = data_functions.create_path(LOG_PATH, 'segmentation_logs') configure_logger(name="segmentation", console_level='INFO', file_level='INFO', out_path=log_path) logger = logging.getLogger(__name__) def main(): orig_path = os.path.join(DATA_PATH, r'raw_data\with_maskes\image') #orig_path = os.path.join(DATA_PATH, r'segmentation\src2') mask_path = os.path.join(DATA_PATH,r'raw_data\with_maskes\label') dest_path = os.path.join(DATA_PATH,r'raw_data\with_maskes\label-augmented') # mask_path = os.path.join(DATA_PATH, # r'unet_data\training\2019-10-20_19-26-14\raw_pred') # dest_path = os.path.join(DATA_PATH, # r'unet_data\training\2019-10-20_19-26-14')
from work.auxiliary.logger_settings import configure_logger from work.auxiliary import data_functions import os import logging LOG_PATH = os.path.abspath('logs') DATA_PATH = os.path.abspath('data') log_path = data_functions.create_path(LOG_PATH, 'stem_extract') configure_logger(name="stem_extract", console_level='INFO', file_level='INFO', out_path=log_path) logger = logging.getLogger(__name__) def get_test_train(): """ use the src_path to create a test train split of data seperated to clases, where each class has it's own folder. save the test and train results in dest_path :return: """ src_path = os.path.join(DATA_PATH, r'classification_data\from_all\set3\All') dest_path = os.path.join(DATA_PATH, r'classification_data\from_all\set3') data_functions.get_train_test_split(src_path, dest_path, train_name='train',