def __init__(self, config, dataset): self.config = config self.train_dir = config.train_dir log.info("self.train_dir = %s", self.train_dir) # --- input ops --- self.batch_size = config.batch_size self.dataset = dataset check_data_id(dataset, config.data_id) _, self.batch = create_input_ops(dataset, self.batch_size, data_id=config.data_id, is_training=False, shuffle=False) # --- create model --- Model = self.get_model_class(config.model) log.infov("Using Model class : %s", Model) self.model = Model(config) self.global_step = tf.contrib.framework.get_or_create_global_step(graph=None) self.step_op = tf.no_op(name='step_no_op') tf.set_random_seed(1234) session_config = tf.ConfigProto( allow_soft_placement=True, gpu_options=tf.GPUOptions(allow_growth=True), device_count={'GPU': 1}, ) self.session = tf.Session(config=session_config) # --- checkpoint and monitoring --- self.saver = tf.train.Saver(max_to_keep=100) self.checkpoint_path = config.checkpoint_path if self.checkpoint_path is None and self.train_dir: self.checkpoint_path = tf.train.latest_checkpoint(self.train_dir) if self.checkpoint_path is None: log.warn("No checkpoint is given. Just random initialization :-)") self.session.run(tf.global_variables_initializer()) else: log.info("Checkpoint path : %s", self.checkpoint_path) mean_std = np.load('../DatasetCreation/VG/mean_std.npz') self.img_mean = mean_std['img_mean'] self.img_std = mean_std['img_std'] self.coords_mean = mean_std['coords_mean'] self.coords_std = mean_std['coords_std']
def __init__(self, config, dataset, dataset_train): self.config = config self.train_dir = config.train_dir log.info("self.train_dir = %s", self.train_dir) # --- input ops --- self.batch_size = config.batch_size self.dataset = dataset self.dataset_train = dataset_train check_data_id(dataset, config.data_id) _, self.batch = create_input_ops(dataset, self.batch_size, data_id=config.data_id, is_training=False, shuffle=False) (x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data() self.total_y = np.concatenate((y_train,y_test)) # --- create model --- self.model = Model(config) self.global_step = tf.contrib.framework.get_or_create_global_step(graph=None) self.step_op = tf.no_op(name='step_no_op') tf.set_random_seed(123) session_config = tf.ConfigProto( allow_soft_placement=True, gpu_options=tf.GPUOptions(allow_growth=True), device_count={'GPU': 1}, ) self.session = tf.Session(config=session_config) # --- checkpoint and monitoring --- self.saver = tf.train.Saver(max_to_keep=100) self.checkpoint_path = config.checkpoint_path if self.checkpoint_path is None and self.train_dir: self.checkpoint_path = tf.train.latest_checkpoint(self.train_dir) if self.checkpoint_path is None: log.warn("No checkpoint is given. Just random initialization :-)") self.session.run(tf.global_variables_initializer()) else: log.info("Checkpoint path : %s", self.checkpoint_path)
def __init__(self, config, model, dataset): self.config = config self.model = model self.train_dir = config.train_dir log.info("self.train_dir = %s", self.train_dir) # --- input ops --- self.batch_size = config.batch_size #############################################################################33 self.dataset = dataset[0] check_data_id(dataset[0], config.data_id) _, self.batch = create_input_ops(dataset[0], self.batch_size, data_id=config.data_id, is_training=False, shuffle=False) ############# here for 10 cross validation ################### ################################################################################### self.global_step = tf.contrib.framework.get_or_create_global_step( graph=None) self.step_op = tf.no_op(name='step_no_op') tf.set_random_seed(1234) session_config = tf.ConfigProto( allow_soft_placement=True, gpu_options=tf.GPUOptions(allow_growth=True), device_count={'GPU': 1}, ) self.session = tf.Session(config=session_config) # --- checkpoint and monitoring --- self.saver = tf.train.Saver(max_to_keep=100) self.checkpoint = config.checkpoint if self.checkpoint is None and self.train_dir: self.checkpoint = tf.train.latest_checkpoint(self.train_dir) if self.checkpoint is None: log.warn("No checkpoint is given. Just random initialization :-)") self.session.run(tf.global_variables_initializer()) else: log.info("Checkpoint path : %s", self.checkpoint)
def __init__(self, config, dataset): self.config = config self.train_dir = config.train_dir log.info("self.train_dir = %s", self.train_dir) # --- input ops --- self.batch_size = config.batch_size self.dataset = dataset check_data_id(dataset, config.data_id) _, self.batch = create_input_ops(dataset, self.batch_size, data_id=config.data_id, num_threads=1, is_training=False, shuffle=False) # --- create model --- self.model = Model(config) self.global_step = tf.contrib.framework.get_or_create_global_step( graph=None) self.step_op = tf.no_op(name='step_no_op') tf.set_random_seed(1234) session_config = tf.ConfigProto( allow_soft_placement=True, gpu_options=tf.GPUOptions(allow_growth=True), device_count={'GPU': 1}, ) self.session = tf.Session(config=session_config) # --- checkpoint and monitoring --- self.saver = tf.train.Saver(max_to_keep=1000) self.checkpoint_path = config.checkpoint_path if self.checkpoint_path is None and self.train_dir: self.checkpoint_path = tf.train.latest_checkpoint(self.train_dir) log.info("Checkpoint path : %s", self.checkpoint_path)