softmax分类

鸢尾花数据集。在数据集包含三个特征值及其三个可能的输出类（不同的鸢尾花），因此权值矩阵的维数应为4*3（下载链接)

import tensorflow as tf

#此时，权值构成了一个矩阵，而非向量，每个“特征权值列"对应一个输出类别
W = tf.Variable(tf.zeros([4, 3]), name = "Weights")
#每个偏置也是如此，每个偏置对应一个输出类
b = tf.Variable(tf.zeros([3]), name = "bias")

def inference(X):
    return tf.nn.softmax(combine_inputs(X))

def loss(X, Y):
    return tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(logits=combine_inputs(X), labels=Y))
def read_csv(batch_size, file_name, record_defaults):

    filename_queue = tf.train.string_input_producer(["iris.csv"])

    reader = tf.TextLineReader()
    key, value = reader.read(filename_queue)

    decoded = tf.decode_csv(value, record_defaults=record_defaults)  # 字符串(文本行)转换到指定默认值张量列元组，为每列设置数据类型


    return tf.train.shuffle_batch(decoded, batch_size=batch_size, capacity=batch_size * 50,
                                  min_after_dequeue=batch_size)  # 读取文件，加载张量batch_size行
def inputs():
    sepal_length, sepal_width, petal_length, petal_width, label = read_csv(100, "iris.data", [[0.0],[0.0],[0.0],[0.0],[""]])
    label_number = tf.to_int32(tf.argmax(tf.to_int32(tf.stack([
        tf.equal(label,["Iris-setosa"]),
        tf.equal(label,["Iris-versicolor"]),
        tf.equal(label,["Iris-virginica"])
    ])),0))

    features = tf.transpose(tf.stack([ sepal_length, sepal_width, petal_length, petal_width]))
    return features, label_number

def combine_inputs(X):
    return tf.matmul(X, W) + b

def train(tol_loss):
    learning_rate = 0.01
    return tf.train.GradientDescentOptimizer(learning_rate).minimize(tol_loss)

def evaluate(sess, X, Y):
    predicted = tf.cast(tf.argmax(inference(X), 1), tf.int32)
    print sess.run( tf.reduce_mean(tf.cast(tf.equal(predicted, Y), tf.float32)))

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    X, Y = inputs()
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)

    tol_loss = loss(X, Y)
    train_op = train(tol_loss)

    train_step = 1001
    for step in range(train_step):
        sess.run(train_op)
        if step % 100 == 0:
            print "%d loss" %step,  sess.run(tol_loss)

    evaluate(sess, X, Y)

    coord.request_stop()
    coord.join(threads)