dragnet_nn_train.py

#!/usr/bin/python3

import argparse

import tensorflow as tf

from dragnet_nn.data_loader import data_loader
from dragnet_nn.dragnet_nn import *

def main(overwrite_brain = False):
    train_loader = data_loader("./training_set_data/matrices_train.txt", "./training_set_data/labels_train.txt")
    test_loader = data_loader("./training_set_data/matrices_test.txt", "./training_set_data/labels_test.txt")
    test_matrices, test_labels = test_loader.all_data()

    dimension = 900
    evidence_classes = 76

    x = tf.placeholder(tf.float32, [None, dimension])

    W_conv1 = weight_variable([5, 5, 1, 32])
    b_conv1 = bias_variable([32])

    x_image = tf.reshape(x, [-1,30,30,1])

    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
    h_pool1 = max_pool_2x2(h_conv1)

    W_conv2 = weight_variable([5, 5, 32, 64])
    b_conv2 = bias_variable([64])

    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
    h_pool2 = max_pool_2x2(h_conv2)

    W_fc1 = weight_variable([8 * 8 * 64, 1024])
    b_fc1 = bias_variable([1024])

    h_pool2_flat = tf.reshape(h_pool2, [-1, 8*8*64])
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

    keep_prob = tf.placeholder(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

    W_fc2 = weight_variable([1024, evidence_classes])
    b_fc2 = bias_variable([evidence_classes])

    y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

    y_ = tf.placeholder(tf.float32, [None, evidence_classes])
    cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))

    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
    correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    saver = tf.train.Saver()
    sess = tf.InteractiveSession()
    sess.run(tf.global_variables_initializer())

    for i in range(20000):
        batch = train_loader.next_batch_rolling(50)
        if i % 100 == 0:
            train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})
            print("step %d, training accuracy %g"%(i, train_accuracy))
        train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

    if overwrite_brain:
        saver.save(sess, DRAGNET_NN_BRAIN_LOCATION + "dragnet_brain.ckpt")
    
    print("test accuracy %g"%accuracy.eval(feed_dict={x: test_matrices, y_: test_labels, keep_prob: 1.0}))
    sess.close()


if __name__ == "__main__":
    
    parser = argparse.ArgumentParser()
    parser.add_argument("--overwrite_brain", help="overwrite current training data. default is false.", action="store_true")
    args = parser.parse_args()

    if args.overwrite_brain:
        main(True)
    else:
        main(False)