我对softmax
, 的输入y = tf.nn.softmax(tf.matmul(x, W) + b)
是一个有值矩阵
tf.matmul(x, W) + b =
[[ 9.77206726e+02]
[ 5.72391296e+02]
[ 3.53560760e+02]
[ 4.75727379e-01]
[ 6.58911804e+02]]
但是当它被输入时softmax
,我得到:
tf.nn.softmax(tf.matmul(x, W) + b) =
[[ 1.]
[ 1.]
[ 1.]
[ 1.]
[ 1.]]
导致我的训练输出是一个1
s 数组,这意味着每批训练数据的权重W
或偏差都不会更新。b
这也导致我的准确性是1
在一组随机的测试数据上
下面是我的代码:
x = tf.placeholder(tf.float32, [None, 2])
W = tf.Variable(tf.random_normal([2, 1]))
b = tf.Variable(tf.random_normal([1]))
y = tf.nn.softmax(tf.matmul(x, W) + b)
## placeholder for cross-entropy
y_ = tf.placeholder(tf.float32, [None, 1])
## cross-entropy function
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
## backpropagation & gradienct descent
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
## initialize variables
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
ITER_RANGE = 10
EVAL_BATCH_SIZE = ( len(training_outputs)/ITER_RANGE )
training_outputs = np.reshape(training_outputs, (300, 1))
## training
for i in range(ITER_RANGE):
print 'iterator:'
print i
## batch out training data
BEGIN = ( i*EVAL_BATCH_SIZE )
END = ( (i*EVAL_BATCH_SIZE) + EVAL_BATCH_SIZE )
batch_ys = training_outputs[BEGIN:END]
batch_xs = training_inputs[BEGIN:END]
print 'batch_xs'
print batch_xs
print 'batch_ys'
print batch_ys
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
# y = tf.nn.softmax(tf.matmul(x, W) + b)
print 'y'
print (sess.run(y, feed_dict={x: batch_xs, y_: batch_ys}))
#print 'x'
#print sess.run(x)
print 'W'
print sess.run(W)
print 'b'
print sess.run(b)
print 'tf.matmul(x, W) + b'
print sess.run(tf.matmul(x, W) + b, feed_dict={x: batch_xs, y_: batch_ys})
print 'tf.nn.softmaxtf.matmul(x, W) + b)'
print sess.run((tf.nn.softmax(tf.matmul(x, W) + b)), feed_dict={x: batch_xs, y_: batch_ys})
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
test_outputs = np.random.rand(300, 1)
## the following prints 1
print(sess.run(accuracy, feed_dict={x: test_inputs, y_: test_outputs}))