我只是在学习TensorFlow,很抱歉,如果这很明显的话。我已经检查了文档并进行了相当多的实验,但我似乎无法让它工作。
def train_network():
OUT_DIMS = 1
FIN_SIZE = 500
x = tf.placeholder(tf.float32, [OUT_DIMS, FIN_SIZE], name="x")
w = tf.Variable(tf.zeros([FIN_SIZE, OUT_DIMS]), name="w")
b = tf.Variable(tf.zeros([OUT_DIMS]), name="b")
y = tf.tanh(tf.matmul(x, w) + b)
yhat = tf.placeholder(tf.float32, [None, OUT_DIMS])
cross_entropy = -tf.reduce_sum(yhat*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
# Launch the model
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
for this_x, this_y in yield_financials():
sess.run(train_step, feed_dict={x: this_x,
yhat: this_y})
print(end=".")
sys.stdout.flush()
yield_financials()输出一个由500个数字组成的numpy数组以及我想要它猜测的数字。我试过洗掉OUT_DIMS和FIN_SIZE,我尝试将它们分批堆积以更接近地匹配教程的样子,我尝试将OUT_DIMS设置为0,完全删除它,我尝试用其他数字替换None,但是没有制作任何进展。
答案 0 :(得分:2)
尝试
this_x = np.reshape(this_x,(1, FIN_SIZE))
sess.run(train_step, feed_dict={x: this_x,
yhat: this_y})
答案 1 :(得分:0)
我有同样的问题,我解决了这个问题。我希望它对你有帮助。
首先,我将加载数据转换为:
train_data = np.genfromtxt(train_data1, delimiter=',')
train_label = np.transpose(train_label1, delimiter=',')
test_data = np.genfromtxt(test_data1, delimiter=',')
test_label = np.transpose(test_label1, delimiter=',')
然后,将trX,trY,teX,teY数据转换为:
# convert the data
trX, trY, teX, teY = train_data,train_label, test_data, test_label
temp = trY.shape
trY = trY.reshape(temp[0], 1)
trY = np.concatenate((1-trY, trY), axis=1)
temp = teY.shape
teY = teY.reshape(temp[0], 1)
teY = np.concatenate((1-teY, teY), axis=1)
最后,我将会话中的图形转换为:
with tf.Session() as sess:
# you need to initialize all variables
tf.initialize_all_variables().run()
for i in range(100):
sess.run(train_op, feed_dict={X: trX, Y: trY})
print(i, np.mean(np.argmax(teY, axis=1) == sess.run(predict_op, feed_dict={X: teX})))
这就是全部。