Function main

ann_class2/tensorflow2.py:26–105

()

# copy this first part from theano2.py
def main():
    # step 1: get the data and define all the usual variables
    Xtrain, Xtest, Ytrain, Ytest = get_normalized_data()

    max_iter = 15
    print_period = 50

    lr = 0.00004
    reg = 0.01

    Ytrain_ind = y2indicator(Ytrain)
    Ytest_ind = y2indicator(Ytest)

    N, D = Xtrain.shape
    batch_sz = 500
    n_batches = N // batch_sz

    # add an extra layer just for fun
    M1 = 300
    M2 = 100
    K = 10
    W1_init = np.random.randn(D, M1) / np.sqrt(D)
    b1_init = np.zeros(M1)
    W2_init = np.random.randn(M1, M2) / np.sqrt(M1)
    b2_init = np.zeros(M2)
    W3_init = np.random.randn(M2, K) / np.sqrt(M2)
    b3_init = np.zeros(K)


    # define variables and expressions
    X = tf.placeholder(tf.float32, shape=(None, D), name='X')
    T = tf.placeholder(tf.float32, shape=(None, K), name='T')
    W1 = tf.Variable(W1_init.astype(np.float32))
    b1 = tf.Variable(b1_init.astype(np.float32))
    W2 = tf.Variable(W2_init.astype(np.float32))
    b2 = tf.Variable(b2_init.astype(np.float32))
    W3 = tf.Variable(W3_init.astype(np.float32))
    b3 = tf.Variable(b3_init.astype(np.float32))

    # define the model
    Z1 = tf.nn.relu( tf.matmul(X, W1) + b1 )
    Z2 = tf.nn.relu( tf.matmul(Z1, W2) + b2 )
    Yish = tf.matmul(Z2, W3) + b3 # remember, the cost function does the softmaxing! weird, right?

    # softmax_cross_entropy_with_logits take in the "logits"
    # if you wanted to know the actual output of the neural net,
    # you could pass "Yish" into tf.nn.softmax(logits)
    cost = tf.reduce_sum(tf.nn.softmax_cross_entropy_with_logits_v2(logits=Yish, labels=T))

    # we choose the optimizer but don't implement the algorithm ourselves
    # let's go with RMSprop, since we just learned about it.
    # it includes momentum!
    train_op = tf.train.RMSPropOptimizer(lr, decay=0.99, momentum=0.9).minimize(cost)

    # we'll use this to calculate the error rate
    predict_op = tf.argmax(Yish, 1)

    costs = []