我在 Tensorflow 中的 RBF 网络有问题吗? [英] Problems with my RBF Network in Tensorflow?
问题描述
我正在使用 Tensorflow 在 RBF 网络上工作，但是在第 112 行出现了这个错误，它说: ValueError: 无法为 Tensor 'Placeholder:0' 提供形状 (40, 13) 的值，它有形状 '(?, 12)'
下面是我的代码.我按照
I'm working on an RBF network using Tensorflow, but there's this error that comes up at line 112 that says this: ValueError: Cannot feed value of shape (40, 13) for Tensor 'Placeholder:0', which has shape '(?, 12)'
Here's my code below. I created my own activation function for my RBF network by following this tutorial. Also, if there is anything else you notice that needs to be fixed, please point it out to me, because I am very new to Tensorflow so it would be helpful to get any feedback I can get.
import tensorflow as tf
import numpy as np
import math
from sklearn import datasets
from sklearn.model_selection import train_test_split
from tensorflow.python.framework import ops
ops.reset_default_graph()
RANDOM_SEED = 42
tf.set_random_seed(RANDOM_SEED)
boston = datasets.load_boston()
data = boston["data"]
target = boston["target"]
N_INSTANCES = data.shape[0]
N_INPUT = data.shape[1] - 1
N_CLASSES = 3
TEST_SIZE = 0.1
TRAIN_SIZE = int(N_INSTANCES * (1 - TEST_SIZE))
batch_size = 40
training_epochs = 400
learning_rate = 0.001
display_step = 20
hidden_size = 200
target_ = np.zeros((N_INSTANCES, N_CLASSES))
data_train, data_test, target_train, target_test = train_test_split(data, target_, test_size=0.1, random_state=100)
x_data = tf.placeholder(shape=[None, N_INPUT], dtype=tf.float32)
y_target = tf.placeholder(shape=[None, N_CLASSES], dtype=tf.float32)
# creates activation function
def gaussian_function(input_layer):
initial = math.exp(-2*math.pow(input_layer, 2))
return initial
np_gaussian_function = np.vectorize(gaussian_function)
def d_gaussian_function(input_layer):
initial = -4 * input_layer * math.exp(-2*math.pow(input_layer, 2))
return initial
np_d_gaussian_function = np.vectorize(d_gaussian_function)
np_d_gaussian_function_32 = lambda input_layer: np_d_gaussian_function(input_layer).astype(np.float32)
def tf_d_gaussian_function(input_layer, name=None):
with ops.name_scope(name, "d_gaussian_function", [input_layer]) as name:
y = tf.py_func(np_d_gaussian_function_32, [input_layer],[tf.float32], name=name, stateful=False)
return y[0]
def py_func(func, inp, Tout, stateful=True, name=None, grad=None):
rnd_name = 'PyFunGrad' + str(np.random.randint(0, 1E+8))
tf.RegisterGradient(rnd_name)(grad)
g = tf.get_default_graph()
with g.gradient_override_map({"PyFunc": rnd_name}):
return tf.py_func(func, inp, Tout, stateful=stateful, name=name)
def gaussian_function_grad(op, grad):
input_variable = op.inputs[0]
n_gr = tf_d_gaussian_function(input_variable)
return grad * n_gr
np_gaussian_function_32 = lambda input_layer: np_gaussian_function(input_layer).astype(np.float32)
def tf_gaussian_function(input_layer, name=None):
with ops.name_scope(name, "gaussian_function", [input_layer]) as name:
y = py_func(np_gaussian_function_32, [input_layer], [tf.float32], name=name, grad=gaussian_function_grad)
return y[0]
# end of defining activation function
def rbf_network(input_layer, weights):
layer1 = tf.matmul(tf_gaussian_function(input_layer), weights['h1'])
layer2 = tf.matmul(tf_gaussian_function(layer1), weights['h2'])
output = tf.matmul(tf_gaussian_function(layer2), weights['output'])
return output
weights = {
'h1': tf.Variable(tf.random_normal([N_INPUT, hidden_size], stddev=0.1)),
'h2': tf.Variable(tf.random_normal([hidden_size, hidden_size], stddev=0.1)),
'output': tf.Variable(tf.random_normal([hidden_size, N_CLASSES], stddev=0.1))
}
pred = rbf_network(x_data, weights)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y_target))
my_opt = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y_target, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
init = tf.global_variables_initializer()
sess = tf.InteractiveSession()
sess.run(init)
# Training loop
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(data_train.shape[0] / batch_size)
for i in range(total_batch):
randidx = np.random.randint(int(TRAIN_SIZE), size=batch_size)
batch_xs = data_train[randidx, :]
batch_ys = target_train[randidx, :]
sess.run(my_opt, feed_dict={x_data: batch_xs, y_target: batch_ys})
avg_cost += sess.run(cost, feed_dict={x_data: batch_xs, y_target: batch_ys})/total_batch
if epoch % display_step == 0:
print("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
train_accuracy = sess.run(accuracy, feed_dict={x_data: batch_xs, y_target: batch_ys})
print("Training accuracy: %.3f" % train_accuracy)
test_acc = sess.run(accuracy, feed_dict={x_data: data_test, y_target: target_test})
print("Test accuracy: %.3f" % (test_acc))
sess.close()
As it has been said, you should have N_Input = data.shape[1].
Actually data.shape[0] relates the number of realisations you have in your data-set and data.shape[1] tells us how many features the network should consider.
The number of features is by definition the size of the input layer regardless how many data you will propose (via feed_dict) to your network.
Plus boston dataset is a regression problem while softmax_cross_entropy is a cost function for classification problem. You can try tf.square to evaluate the euclidean distance between what you are predicting and what you want :
cost = tf.reduce_mean(tf.square(pred - y_target))
You will see that your network is learning, even though the accuracy is not very high.
Edit :
Your code is actually learning well but you used the wrong tool to measure it.
Mainly, your errors still reside in the fact that you are dealing with regression problem not with a classification problem.
In classification problem you can evaluate the accuracy of your on-going learning process using
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y_target, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
It consists in checking if the predicted class is the same as the expected class, for an input among x_test.
In regression problem, doing so is senseless since you are looking for a real number i.e. an infinity of possibility from the classification point of view.
In regression problem you can estimate the error (mean or whatever) between predicted values and expected values. We can use what I suggested below :
cost = tf.reduce_mean(tf.square(pred - y_target))
I modified your code consequently here it is
pred = rbf_network(x_data, weights)
cost = tf.reduce_mean(tf.square(pred - y_target))
my_opt = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
#correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y_target, 1))
#accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
init = tf.global_variables_initializer()
sess = tf.InteractiveSession()
sess.run(init)
plt.figure("Error evolution")
plt.xlabel("N_epoch")
plt.ylabel("Error evolution")
tol = 5e-4
epoch, err=0, 1
# Training loop
while epoch <= training_epochs and err >= tol:
avg_cost = 0.
total_batch = int(data_train.shape[0] / batch_size)
for i in range(total_batch):
randidx = np.random.randint(int(TRAIN_SIZE), size=batch_size)
batch_xs = data_train[randidx, :]
batch_ys = target_train[randidx, :]
sess.run(my_opt, feed_dict={x_data: batch_xs, y_target: batch_ys})
avg_cost += sess.run(cost, feed_dict={x_data: batch_xs, y_target: batch_ys})/total_batch
plt.plot(epoch, avg_cost, marker='o', linestyle="none", c='k')
plt.pause(0.05)
err = avg_cost
if epoch % 10 == 0:
print("Epoch: {}/{} err = {}".format(epoch, training_epochs, avg_cost))
epoch +=1
print ("End of learning process")
print ("Final epoch = {}/{} ".format(epoch, training_epochs))
print ("Final error = {}".format(err) )
sess.close()
The output is
Epoch: 0/400 err = 0.107879924503
Epoch: 10/400 err = 0.00520248359747
Epoch: 20/400 err = 0.000651647908274
End of learning process
Final epoch = 26/400
Final error = 0.000474644409471
We plot the evolution of the error in the training through the different epochs
这篇关于我在 Tensorflow 中的 RBF 网络有问题吗?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
