我试图实现一个神经网络来解决分类问题,但是我的程序:
_, c = sess.run([train_op, loss_op], feed_dict={X: x_train,Y: y_train})
我试图重塑数据,并尝试了许多堆栈中给出的解决方案来解决我的问题,但对我不起作用,我想知道我该怎么办?
最重要的部分:
...
n_output = 8
n_input = 9 # Max number of input that may have features of one single program
################################ Dfine data ####################################
from google.colab import files
import io
uploaded = files.upload()
x_train_ = pd.read_csv(io.StringIO(uploaded['x_train.csv'].decode('utf-8')), skiprows=1, header=None)
uploaded1 = files.upload()
y_train_ = pd.read_csv(io.StringIO(uploaded1['y_train.csv'].decode('utf-8')), skiprows=1, header=None)
x_train.fillna(-1, inplace=True)
x_train = np.array(x_train)
y_train = np.array(y_train)
################################ Input, weights, biases ########################
# tf Graph input
X = tf.placeholder(shape=[None, n_input], dtype=tf.float32)
Y = tf.placeholder(shape=[None, n_output], dtype=tf.float32)
.....
################################ Construct model ###############################
logits = multilayer_perceptron(X)
# Define loss and optimizer
loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
train_op = optimizer.minimize(loss_op)
...
# Initializing the variables
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
# Training cycle
for epoch in range(training_epochs):
avg_cost = 0.
_, c = sess.run([train_op, loss_op], feed_dict={X: x_train,Y: y_train})
...
print("Optimization Finished!")
编辑:一旦我打印出:print(y_train_.head())
,它就会给出:
0
0 2
1 4
2 8
3 16
4 32
发布于 2019-04-11 19:24:35
后来我意识到,因为我的y_train csv文件只包含一列,所以我必须这样声明它
Y = tf.placeholder(shape=[None,1], dtype=tf.float32)
我不应该混淆类的数量和如何声明"Y“。
就像他说的那样,如果我这样声明Y:
Y = tf.placeholder(shape=[None, n_output], dtype=tf.float32)
我的Y占位符的形状是m,8,而不是m,1。所以我必须像上面的解决方案一样声明它来修复它。
发布于 2019-04-10 02:26:43
Y = tf.placeholder(shape=[None, n_output], dtype=tf.float32)
使您的Y占位符的形状为m,8。显然,y_train的构造不正确,请尝试y_train.values()而不是np.array(y_train)。
https://stackoverflow.com/questions/55598430
复制相似问题