rng = np.random.RandomState(888) # np.random.seed(423453) base_dir = os.getcwd() # train_csv_path = os.path.join(base_dir,'trainingData.csv') test_csv_path = os.path.join(base_dir, 'validationData.csv') valid_csv_path = os.path.join(base_dir, 'AllValuationData.csv') train_csv_path = os.path.join(base_dir, 'arrAllTrainingData.csv') log_dir = 'DEEPLEARNING_MODEL_log.txt' if __name__ == '__main__': # Load data (train_x, train_y), (valid_x, valid_y), (test_x, test_y) = data_helper.load_data_all( train_csv_path, valid_csv_path, test_csv_path) # train_x, train_y, valid_x, valid_y, test_x, test_y=data_helper.load(train_csv_path, test_csv_path) # patience=[i for i in range(1,50,2)] # patience=[21,] # B=[i for i in np.linspace(3.0,3.1,2)] # for b in B: # for p in patience: # dropout=[i for i in np.linspace(0.4,0.7,4)] dropout = [ 0.7, ] for dp in dropout:
#!/usr/bin/env python import os import time from model_patient import * from data_helper import load_data, load_data_all import tensorflow as tf import numpy as np from tensorflow.examples.tutorials.mnist import input_data batch_size = 128 test_size = 256 allX, allY = load_data_all() word_embedding = np.load('../data/model_50.npy') # print teY # raw_input() py_x, cost = model() # cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(py_x, Y)) train_op = tf.train.RMSPropOptimizer(0.001, 0.9).minimize(cost) predict_op = py_x # print trY.shape # Launch the graph in a session with tf.Session() as sess: # you need to initialize all variables tf.initialize_all_variables().run()