np.set_printoptions(suppress=True) os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' np.random.seed(0) EPOCHES = 100 BATCH_SIZE = 16 learning_rate = 0.0002 # real data # ######################################## difference from tensorflow file_x = '../dsets/P' + str(rtt.mpc_player.id) + "/reg_train_x.csv" file_y = '../dsets/P' + str(rtt.mpc_player.id) + "/reg_train_y.csv" real_X, real_Y = rtt.MpcDataSet(label_owner=1).load_XY(file_x, file_y) # ######################################## difference from tensorflow DIM_NUM = real_X.shape[1] X = tf.placeholder(tf.float64, [None, DIM_NUM]) Y = tf.placeholder(tf.float64, [None, 1]) print(X) print(Y) # initialize W & b W = tf.Variable(tf.zeros([DIM_NUM, 1], dtype=tf.float64)) b = tf.Variable(tf.zeros([1], dtype=tf.float64)) print(W) print(b) # predict
np.set_printoptions(suppress=True) os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' np.random.seed(0) EPOCHES = 100 BATCH_SIZE = 16 learning_rate = 0.0002 # real data # ######################################## difference from tensorflow file_x = '../dsets/P' + str(rtt.mpc_player.id) + "/cls_train_x.csv" file_y = '../dsets/P' + str(rtt.mpc_player.id) + "/cls_train_y.csv" real_X, real_Y = rtt.MpcDataSet(label_owner=0).load_XY(file_x, file_y, header=None) # ######################################## difference from tensorflow real_X = real_X[:100, :] real_Y = real_Y[:100, :] DIM_NUM = real_X.shape[1] X = tf.placeholder(tf.float64, [None, DIM_NUM]) Y = tf.placeholder(tf.float64, [None, 1]) print(X) print(Y) # initialize W & b W = tf.Variable(tf.zeros([DIM_NUM, 1], dtype=tf.float64)) b = tf.Variable(tf.zeros([1], dtype=tf.float64)) print(W)