2017-04-01 7 views
1

私が抱えているパフォーマンスの問題を特定するには、何か助けが必要です。私はhttps://codesachin.wordpress.com/2015/11/28/self-organizing-maps-with-googles-tensorflow/のコードを自己組織化マップのベースとして使用しています。このコードはCPUで10秒、GPUで40秒かかる。私はログを有効にし、テンソルボード内の変数の名前を関連付けるようにコードを修正しましたが、このパフォーマンスの問題の原因を特定できません。あなたは何が起こっているかもしれないかのヒントを教えてください。私はTensorflowの最新バージョンで実行するようにコードを変換しました。TensorFlow Self Organizing Mapsのパフォーマンスに関する問題を特定してください

ありがとうございました。

コードが変更されました。

import tensorflow as tf 
import numpy as np 


class SOM(object): 
    """ 
    2-D Self-Organizing Map with Gaussian Neighbourhood function 
    and linearly decreasing learning rate. 
    """ 

    # To check if the SOM has been trained 
    _trained = False 

    def __init__(self, m, n, dim, n_iterations=100, alpha=None, sigma=None): 
     """" 
     Initializes all necessary components of the TensorFlow 
     Graph. 

     m X n are the dimensions of the SOM. 'n_iterations' should 
     should be an integer denoting the number of iterations undergone 
     while training. 
     'dim' is the dimensionality of the training inputs. 
     'alpha' is a number denoting the initial time(iteration no)-based 
     learning rate. Default value is 0.3 
     'sigma' is the the initial neighbourhood value, denoting 
     the radius of influence of the BMU while training. By default, its 
     taken to be half of max(m, n). 
     """ 

     # Assign required variables first 
     self._m = m 
     self._n = n 
     if alpha is None: 
      alpha = 0.3 
     else: 
      alpha = float(alpha) 
     if sigma is None: 
      sigma = max(m, n)/2.0 
     else: 
      sigma = float(sigma) 
     self._n_iterations = abs(int(n_iterations)) 

     ##INITIALIZE GRAPH 
     self._graph = tf.Graph() 

     ##POPULATE GRAPH WITH NECESSARY COMPONENTS 
     with self._graph.as_default(): 

      ##VARIABLES AND CONSTANT OPS FOR DATA STORAGE 

      # Randomly initialized weightage vectors for all neurons, 
      # stored together as a matrix Variable of size [m*n, dim] 
      self._weightage_vects = tf.Variable(tf.random_normal(
       [m * n, dim])) 

      # Matrix of size [m*n, 2] for SOM grid locations 
      # of neurons 
      self._location_vects = tf.constant(np.array(
       list(self._neuron_locations(m, n)))) 

      ##PLACEHOLDERS FOR TRAINING INPUTS 
      # We need to assign them as attributes to self, since they 
      # will be fed in during training 

      # The training vector 
      self._vect_input = tf.placeholder("float", [dim]) 
      # Iteration number 
      self._iter_input = tf.placeholder("float") 

      ##CONSTRUCT TRAINING OP PIECE BY PIECE 
      # Only the final, 'root' training op needs to be assigned as 
      # an attribute to self, since all the rest will be executed 
      # automatically during training 

      # To compute the Best Matching Unit given a vector 
      # Basically calculates the Euclidean distance between every 
      # neuron's weightage vector and the input, and returns the 
      # index of the neuron which gives the least value 
      bmu_index = tf.argmin(tf.sqrt(tf.reduce_sum(
       tf.pow(tf.subtract(self._weightage_vects, tf.stack(
        [self._vect_input for i in range(m * n)])), 2), 1)), 
       0) 

      # This will extract the location of the BMU based on the BMU's 
      # index 
      slice_input = tf.pad(tf.reshape(bmu_index, [1]), 
           np.array([[0, 1]])) 
      bmu_loc = tf.reshape(tf.slice(self._location_vects, slice_input, 
              tf.constant(np.array([1, 2]), dtype=tf.int64)), 
           [2]) 

      # To compute the alpha and sigma values based on iteration 
      # number 
      learning_rate_op = tf.subtract(1.0, tf.div(self._iter_input, 
                 self._n_iterations)) 
      _alpha_op = tf.multiply(alpha, learning_rate_op) 
      _sigma_op = tf.multiply(sigma, learning_rate_op) 

      # Construct the op that will generate a vector with learning 
      # rates for all neurons, based on iteration number and location 
      # wrt BMU. 
      bmu_distance_squares = tf.reduce_sum(tf.pow(tf.subtract(
       self._location_vects, tf.stack(
        [bmu_loc for i in range(m * n)])), 2), 1) 
      neighbourhood_func = tf.exp(tf.negative(tf.div(tf.cast(
       bmu_distance_squares, "float32"), tf.pow(_sigma_op, 2)))) 
      learning_rate_op = tf.multiply(_alpha_op, neighbourhood_func) 

      # Finally, the op that will use learning_rate_op to update 
      # the weightage vectors of all neurons based on a particular 
      # input 
      learning_rate_multiplier = tf.stack([tf.tile(tf.slice(
       learning_rate_op, np.array([i]), np.array([1])), [dim]) 
       for i in range(m * n)]) 
      weightage_delta = tf.multiply(
       learning_rate_multiplier, 
       tf.subtract(tf.stack([self._vect_input for i in range(m * n)]), 
          self._weightage_vects)) 
      new_weightages_op = tf.add(self._weightage_vects, 
             weightage_delta) 
      self._training_op = tf.assign(self._weightage_vects, 
              new_weightages_op) 

      ##INITIALIZE SESSION 
      self._sess = tf.Session(config=tf.ConfigProto(log_device_placement=True)) 

      ##INITIALIZE VARIABLES 
      init_op = tf.global_variables_initializer() 
      self._sess.run(init_op) 

    def _neuron_locations(self, m, n): 
     """ 
     Yields one by one the 2-D locations of the individual neurons 
     in the SOM. 
     """ 
     # Nested iterations over both dimensions 
     # to generate all 2-D locations in the map 
     for i in range(m): 
      for j in range(n): 
       yield np.array([i, j]) 

    def train(self, input_vects): 
     """ 
     Trains the SOM. 
     'input_vects' should be an iterable of 1-D NumPy arrays with 
     dimensionality as provided during initialization of this SOM. 
     Current weightage vectors for all neurons(initially random) are 
     taken as starting conditions for training. 
     """ 

     # Training iterations 
     for iter_no in range(self._n_iterations): 
      # Train with each vector one by one 
      for input_vect in input_vects: 
       self._sess.run(self._training_op, 
           {self._vect_input: input_vect, 
           self._iter_input: iter_no}) 

     # Store a centroid grid for easy retrieval later on 
     centroid_grid = [[] for i in range(self._m)] 
     self._weightages = list(self._sess.run(self._weightage_vects)) 
     self._locations = list(self._sess.run(self._location_vects)) 
     for i, loc in enumerate(self._locations): 
      centroid_grid[loc[0]].append(self._weightages[i]) 
     self._centroid_grid = centroid_grid 

     self._trained = True 

    def get_centroids(self): 
     """ 
     Returns a list of 'm' lists, with each inner list containing 
     the 'n' corresponding centroid locations as 1-D NumPy arrays. 
     """ 
     if not self._trained: 
      raise ValueError("SOM not trained yet") 
     return self._centroid_grid 

    def map_vects(self, input_vects): 
     """ 
     Maps each input vector to the relevant neuron in the SOM 
     grid. 
     'input_vects' should be an iterable of 1-D NumPy arrays with 
     dimensionality as provided during initialization of this SOM. 
     Returns a list of 1-D NumPy arrays containing (row, column) 
     info for each input vector(in the same order), corresponding 
     to mapped neuron. 
     """ 

     if not self._trained: 
      raise ValueError("SOM not trained yet") 

     to_return = [] 
     for vect in input_vects: 
      min_index = min([i for i in range(len(self._weightages))], 
          key=lambda x: np.linalg.norm(vect - 
                 self._weightages[x])) 
      to_return.append(self._locations[min_index]) 

     return to_return 

    def write(self): 
     writer = tf.summary.FileWriter('/tmp/tensorflow_logs', graph=self._sess.graph) 


# For plotting the images 
from matplotlib import pyplot as plt 

# Training inputs for RGBcolors 
colors = np.array(
    [[0., 0., 0.], 
    [0., 0., 1.], 
    [0., 0., 0.5], 
    [0.125, 0.529, 1.0], 
    [0.33, 0.4, 0.67], 
    [0.6, 0.5, 1.0], 
    [0., 1., 0.], 
    [1., 0., 0.], 
    [0., 1., 1.], 
    [1., 0., 1.], 
    [1., 1., 0.], 
    [1., 1., 1.], 
    [.33, .33, .33], 
    [.5, .5, .5], 
    [.66, .66, .66]]) 
color_names = \ 
    ['black', 'blue', 'darkblue', 'skyblue', 
    'greyblue', 'lilac', 'green', 'red', 
    'cyan', 'violet', 'yellow', 'white', 
    'darkgrey', 'mediumgrey', 'lightgrey'] 

with tf.device("/cpu:0"): 
    # Train a 20x30 SOM with 400 iterations 
    som = SOM(20, 30, 3, 400) 
    som.train(colors) 

    # Get output grid 
    image_grid = som.get_centroids() 

    # Map colours to their closest neurons 
    mapped = som.map_vects(colors) 

    # Plot 
    plt.imshow(image_grid) 
    plt.title('Color SOM') 
    for i, m in enumerate(mapped): 
     plt.text(m[1], m[0], color_names[i], ha='center', va='center', 
       bbox=dict(facecolor='white', alpha=0.5, lw=0)) 
    plt.show() 
    som.write() 
+0

GPUで計算が非常に遅い場合は、GPUとの間でデータをやりとりするために多くの時間が費やされているためです(たとえば、フィードやフェッチなどですが、中央のCPUのみの操作アクセルレーターで走ることから得られるスピードアップよりも)この[docsトピック](http://stackoverflow.com/documentation/tensorflow/3850/measure-the-execution-time-of-individual-operations#t=201704031523532143089)には、細かい部分を抽出するためのステップバイステップガイドがあります。 'sess.run()'呼び出しから得られたパフォーマンスデータを正確に把握するのに役立ちます。 – mrry

答えて

0

他の投稿を見ると、それを解決したようです。それは他の誰かを助けている場合、私はまた、更新機能を変更することでパフォーマンスを向上させるために管理:1で行うことができ、さらに調整が可能性があります

learning_rate_multiplier = tf.reshape(learning_rate_op, [self._m * self._n, 1])

、これはしかし、はるかに高速に実行しました。

関連する問題