我在TensorFlow中尝试实现K最近邻算法时遇到了困难。我认为要么是我忽略了某个错误，要么是做了一些非常糟糕的事情。
以下代码总是预测Mnist标签为0。
from __future__ import print_functionimport numpy as npimport tensorflow as tf# Import MNIST datafrom tensorflow.examples.tutorials.mnist import input_dataK = 4mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)# In this example, we limit mnist dataXtr, Ytr = mnist.train.next_batch(55000) # whole training setXte, Yte = mnist.test.next_batch(10000) # whole test set# tf Graph Inputxtr = tf.placeholder("float", [None, 784])ytr = tf.placeholder("float", [None, 10])xte = tf.placeholder("float", [784])# Euclidean Distancedistance = tf.neg(tf.sqrt(tf.reduce_sum(tf.square(tf.sub(xtr, xte)), reduction_indices=1)))# Prediction: Get min distance neighborsvalues, indices = tf.nn.top_k(distance, k=K, sorted=False)nearest_neighbors = []for i in range(K): nearest_neighbors.append(np.argmax(ytr[indices[i]]))sorted_neighbors, counts = np.unique(nearest_neighbors, return_counts=True)pred = tf.Variable(nearest_neighbors[np.argmax(counts)])# not works either# neighbors_tensor = tf.pack(nearest_neighbors)# y, idx, count = tf.unique_with_counts(neighbors_tensor)# pred = tf.slice(y, begin=[tf.arg_max(count, 0)], size=tf.constant([1], dtype=tf.int64))[0]accuracy = 0.# Initializing the variablesinit = tf.initialize_all_variables()# Launch the graphwith 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:", nn_index, "True Class:", np.argmax(Yte[i])) # Calculate accuracy if nn_index == np.argmax(Yte[i]): accuracy += 1. / len(Xte) print("Done!") print("Accuracy:", accuracy)任何帮助都将不胜感激。
回答：
总的来说，在定义TensorFlow模型时使用numpy函数并不是一个好主意。这正是你的代码无法工作的原因。我只对你的代码做了两个改动。我用tf.argmax替换了np.argmax。我还删除了#This doesn't work either的注释。
这是完整的工作代码：
from __future__ import print_functionimport numpy as npimport tensorflow as tf# Import MNIST datafrom tensorflow.examples.tutorials.mnist import input_dataK = 4mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)# In this example, we limit mnist dataXtr, Ytr = mnist.train.next_batch(55000) # whole training setXte, Yte = mnist.test.next_batch(10000) # whole test set# tf Graph Inputxtr = tf.placeholder("float", [None, 784])ytr = tf.placeholder("float", [None, 10])xte = tf.placeholder("float", [784])# Euclidean Distancedistance = tf.negative(tf.sqrt(tf.reduce_sum(tf.square(tf.subtract(xtr, xte)), reduction_indices=1)))# Prediction: Get min distance neighborsvalues, indices = tf.nn.top_k(distance, k=K, sorted=False)nearest_neighbors = []for i in range(K): nearest_neighbors.append(tf.argmax(ytr[indices[i]], 0))neighbors_tensor = tf.stack(nearest_neighbors)y, idx, count = tf.unique_with_counts(neighbors_tensor)pred = tf.slice(y, begin=[tf.argmax(count, 0)], size=tf.constant([1], dtype=tf.int64))[0]accuracy = 0.# Initializing the variablesinit = tf.initialize_all_variables()# Launch the graphwith 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, ytr: Ytr, xte: Xte[i, :]}) # Get nearest neighbor class label and compare it to its true label print("Test", i, "Prediction:", nn_index, "True Class:", np.argmax(Yte[i])) #Calculate accuracy if nn_index == np.argmax(Yte[i]): accuracy += 1. / len(Xte) print("Done!") print("Accuracy:", accuracy)