python - TensorFlow模型损失0

import tensorflow as tf
import numpy as np
def weight(shape):
return tf.Variable(tf.truncated_normal(shape, stddev=0.1))
def bias(shape):
return tf.Variable(tf.constant(0.1, shape=shape))
def output(input,w,b):
return tf.matmul(input,w)+b
x_columns = 33
y_columns = 1
layer1_num = 7
layer2_num = 7
epoch_num = 10
train_num = 1000
batch_size = 100
display_size = 1
x = tf.placeholder(tf.float32,[None,x_columns])
y = tf.placeholder(tf.float32,[None,y_columns])

layer1 =
tf.nn.relu(output(x,weight([x_columns,layer1_num]),bias([layer1_num])))
layer2=tf.nn.relu
(output(layer1,weight([layer1_num,layer2_num]),bias([layer2_num])))
prediction = output(layer2,weight([layer2_num,y_columns]),bias([y_columns]))

loss=tf.reduce_mean
(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
train_step = tf.train.AdamOptimizer().minimize(loss)

sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
for epoch in range(epoch_num):
   avg_loss = 0.
   for i in range(train_num):
      index = np.random.choice(len(x_train),batch_size)
      x_train_batch = x_train[index]
      y_train_batch = y_train[index]
      _,c = sess.run([train_step,loss],feed_dict=
{x:x_train_batch,y:y_train_batch})
      avg_loss += c/train_num
   if epoch % display_size == 0:
      print("Epoch:{0},Loss:{1}".format(epoch+1,avg_loss))
print("Training Finished")

我的模特得到
纪元:2，亏损:0.0
纪元:3，亏损:0.0
纪元:4，亏损:0.0
纪元:5，亏损:0.0
纪元:6，亏损:0.0
纪元:7，亏损:0.0
纪元:8，亏损:0.0
纪元:9，亏损:0.0
纪元:10，亏损:0.0
培训结束

我该如何解决这个问题？

最佳答案

softmax_cross_entropy_with_logits期望标签采用一次性格式，即形状为[batch_size, num_classes]。在这里，您有y_columns = 1，这意味着只有1个类，它必须始终是预测的类和“基本事实”(从网络的角度来看)，因此无论权重是多少，您的输出始终是正确的。因此，loss=0。

我猜您确实有不同的类，并且y_train包含标签的ID。然后predictions的形状应为[batch_size, num_classes]，而不是softmax_cross_entropy_with_logits，而应使用 tf.nn.sparse_softmax_cross_entropy_with_logits