train_ratio=model_config.train_ratio, device=device) log_dir = os.path.join('saves', config.model) # Initialize Logger class logger = Logger(log_dir) model_config.save(os.path.join(logger.log_dir, 'config.json')) # Get the position and target of the evaluated item eval_pos, eval_target = dataset.eval_data() # Get the popularity item item_popularity = dataset.item_popularity # Initialize Evaluator class evaluator = Evaluator(eval_pos, eval_target, item_popularity, model_config.top_k) # Build the model model = build_model(config.model, model_config, dataset.num_users, dataset.num_items, device) # Get the model info and data info logger.info(model_config) logger.info(dataset) # Initialize Trainer class trainer = Trainer(dataset=dataset, model=model, evaluator=evaluator, logger=logger, conf=model_config) # Train the model and get results trainer.train(experiment) # Dictionary to store model hyper-parameters hyper_params = {
import tensorflow as tf from Environment import * from ModelBuilder import build_model import os tf.reset_default_graph() layers = [729, 729, 729] inputs, Q_out, predict = build_model(9, layers, 9) sess = tf.Session() env = Environment() saver = tf.train.Saver() init = tf.global_variables_initializer() sess.run(init) checkpoint = tf.train.get_checkpoint_state("model") if checkpoint and checkpoint.model_checkpoint_path: s = saver.restore(sess, checkpoint.model_checkpoint_path) print("Successfully loaded the model:", checkpoint.model_checkpoint_path) step = int( os.path.basename(checkpoint.model_checkpoint_path).split('-')[1]) else: print("Could not find old network weights") player = env.O turn = get_first_turn() done = False state = get_new_board()