import numpy as np
import tensorflow as tf

# Import MINST data
import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
#input_data.py  Dataset downloading Loading the entire dataset into numpy array:
#這裡主要是匯入資料，資料通過input_data.py已經下載到/tmp/data/目錄之下了，這裡下載資料的時候，需要提前用瀏覽器嘗試是否可以開啟
#http://yann.lecun.com/exdb/mnist/，如果打不開，下載資料階段會報錯。而且一旦資料下載中斷，需要將之前下載的未完成的資料清空，重新
#進行下載，否則會出現CRC Check錯誤。read_data_sets是input_data.py裡面的一個函式，主要是將資料解壓之後，放到對應的位置。
# In this example, we limit mnist data
Xtr, Ytr = mnist.train.next_batch(5000) #5000 for training (nn candidates)
Xte, Yte = mnist.test.next_batch(200) #200 for testing
#mnist.train.next_batch，其中train和next_batch都是在input_data.py裡定義好的資料項和函式。此處主要是取得一定數量的資料。
#next_batch
 
 函式可以遍歷整個資料集，只返回所需的樣本資料集的一部分（為了節省記憶體和避免載入整個資料集）。

# Reshape images to 1D
Xtr = np.reshape(Xtr, newshape=(-1, 28*28))
Xte = np.reshape(Xte, newshape=(-1, 28*28))
#將二維的影象資料一維化，利於後面的相加操作。
# tf Graph Input
xtr = tf.placeholder("float", [None, 784])
xte = tf.placeholder("float", [784])
#設立兩個空的型別，並沒有給具體的資料。這也是為了基於這兩個型別，去實現部分的graph。

# Nearest Neighbor calculation using L1 Distance
# Calculate L1 Distance
distance = tf.reduce_sum(tf.abs(tf.add(xtr, tf.neg(xte))), reduction_indices=1)
# Predict: Get min distance index (Nearest neighbor)
pred = tf.arg_min(distance, 0)
#最近鄰居演算法，算最近的距離的鄰居，並且獲取該鄰居的下標，這裡只是基於空的型別，實現的graph，並未進行真實的計算。
accuracy = 0.
# Initializing the variables
init = tf.initialize_all_variables()
#初始化所有的變數和未分配數值的佔位符，這個過程是所有程式中必須做的，否則可能會讀出隨機數值。
# Launch the graph
with tf.Session() as sess:
    sess.run(init)

    # loop over test data
    for i in range(len(Xte)):
        # Get nearest neighbor
        nn_index = sess.run(pred, feed_dict={xtr: Xtr, xte: Xte[i,:]})
        # Get nearest neighbor class label and compare it to its true label
        print "Test", i, "Prediction:", np.argmax(Ytr[nn_index]), "True Class:", np.argmax(Yte[i])
        # Calculate accuracy
        if np.argmax(Ytr[nn_index]) == np.argmax(Yte[i]):
            accuracy += 1./len(Xte)
    print "Done!"
    print "Accuracy:", accuracy
#for迴圈迭代計算每一個測試資料的預測值，並且和真正的值進行對比，並計算精確度。該演算法比較經典的是不需要提前訓練，直接在測試階段進行識別
 

相關API：

tf.reduce_sum(input_tensor, reduction_indices=None, keep_dims=False, name=None)

Computes the sum of elements across dimensions of a tensor.

Reduces input_tensor along the dimensions given in reduction_indices. Unless keep_dims is true, the rank of the tensor is reduced by 1 for each entry in reduction_indices

If reduction_indices has no entries, all dimensions are reduced, and a tensor with a single element is returned.

For example:

# 'x' is [[1, 1, 1]
#         [1, 1, 1]]
tf.reduce_sum(x) ==> 6
tf.reduce_sum(x, 0) ==> [2, 2, 2]
tf.reduce_sum(x, 1) ==> [3, 3]
tf.reduce_sum(x, 1, keep_dims=True) ==> [[3], [3]]
tf.reduce_sum(x, [0, 1]) ==> 6

Args:

• input_tensor: The tensor to reduce. Should have numeric type.
• reduction_indices: The dimensions to reduce. If None (the default), reduces all dimensions.
• keep_dims: If true, retains reduced dimensions with length 1.
• name: A name for the operation (optional).

Returns:

The reduced tensor.