我发现这个对使用 tensorflow 实现自组织地图非常有用的博客。我尝试在其上运行 scikit learn iris 数据集，结果见下图。为了了解 SOM 是如何演变的，我想为我的图表制作动画，这就是我卡住的地方。我找到了一些动画的基本示例：
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.animation as animation
fig2 = plt.figure()
x = np.arange(-9, 10)
y = np.arange(-9, 10).reshape(-1, 1)
base = np.hypot(x, y)
ims = []
for add in np.arange(15):
ims.append((plt.pcolor(x, y, base + add, norm=plt.Normalize(0, 30)),))
im_ani = animation.ArtistAnimation(fig2, ims, interval=50, repeat_delay=3000, blit=True)
plt.show()
要制作动画，我必须编辑 som.py 的 train 函数，因为循环的训练被封装在那里。它看起来像这样：
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.
"""
#fig2 = plt.figure()
#Training iterations
for iter_no in tqdm(range(self._n_iterations)):
#Train with each vector one by one
for input_vect in input_vects:
self._sess.run(self._training_op,
feed_dict={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])
#im_ani = animation.ArtistAnimation(fig2, centroid_grid, interval=50, repeat_delay=3000, blit=True)
self._centroid_grid = centroid_grid
self._trained = True
#plt.show()
评论是我尝试实现动画，但它不起作用，因为在基本示例中，ims 列表是 matplotlib 对象，而在训练函数中，列表是 4d numpy 数组。
总而言之，我怎样才能为我的情节设置动画？提前感谢您的帮助。
这是我的完整代码：
som.py
import tensorflow as tf
import numpy as np
from tqdm import tqdm
import matplotlib.animation as animation
from matplotlib import pyplot as plt
import time
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]))),
[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()
##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.
"""
#fig2 = plt.figure()
#Training iterations
for iter_no in tqdm(range(self._n_iterations)):
#Train with each vector one by one
for input_vect in input_vects:
self._sess.run(self._training_op,
feed_dict={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])
#im_ani = animation.ArtistAnimation(fig2, centroid_grid, interval=50, repeat_delay=3000, blit=True)
self._centroid_grid = centroid_grid
#print(centroid_grid)
self._trained = True
#plt.show()
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 = [self._locations[min([i for i in range(len(self._weightages))],
key=lambda x: np.linalg.norm(vect-self._weightages[x]))] for vect in input_vects]
return to_return
用法.py
from matplotlib import pyplot as plt
import matplotlib.animation as animation
import numpy as np
from som import SOM
from sklearn.datasets import load_iris
data = load_iris()
flower_data = data['data']
normed_flower_data = flower_data / flower_data.max(axis=0)
target_int = data['target']
target_names = data['target_names']
targets = [target_names[i] for i in target_int]
#Train a 20x30 SOM with 400 iterations
som = SOM(25, 25, 4, 100) # My parameters
som.train(normed_flower_data)
#Get output grid
image_grid = som.get_centroids()
#Map colours to their closest neurons
mapped = som.map_vects(normed_flower_data)
#Plot
plt.imshow(image_grid)
plt.title('SOM')
for i, m in enumerate(mapped):
plt.text(m[1], m[0], targets[i], ha='center', va='center',
bbox=dict(facecolor='white', alpha=0.5, lw=0))
plt.show()