我是机器学习的新手。我正在研究Iris数据集。并使用萼片长度，萼片宽度，花瓣长度来预测花瓣宽度使用神经网络。因此，将3个输入节点作为具有偏置b1的A1，将10个隐藏节点作为具有偏置b2和1个输出节点的A2。 此外，x_val_train，x_val_test，y_val_train，y_val_test变量用于训练和测试 主要功能如下。
x_val = np.array([x[0:3] for x in iris.data])
y_val = np.array([x[3] for x in iris.data])
hidden_layer_size = 10
#Generate a 1D array of random numbers range round(len(x_val)*0.8
train_indices = np.random.choice(len(x_val), round(len(x_val)*0.8), replace = False)
#Create a set which does not contain the numbers in train_indices and turn it into array
test_indices = np.array(list(set(range(len(x_val))) - set(train_indices)))
#print("Train Indexes\n",train_indices,test_indices)
x_val_train = x_val[train_indices]
x_val_test = x_val[test_indices]
y_val_train = y_val[train_indices]
y_val_test = y_val[test_indices]
x_data = tf.placeholder(shape=[None, 3], dtype = tf.float32)
y_target = tf.placeholder(shape = [None, 1], dtype = tf.float32) #Figure out usage of None
#Create Layers for NN
A1 = tf.Variable(tf.random_normal(shape = [3,hidden_layer_size])) #Input -> Hidden
b1 = tf.Variable(tf.random_normal(shape = [hidden_layer_size])) #bias in Input for hidden
A2 = tf.Variable(tf.random_normal(shape = [hidden_layer_size,1])) #Hidden -> Output
b2 = tf.Variable(tf.random_normal(shape=[1])) #Hidden Layer Bias
#Generation of Model
hidden_output = tf.nn.relu(tf.add(tf.matmul(x_data,A1),b1))
final_output = tf.nn.relu(tf.add(tf.matmul(hidden_output,A2),b2))
cost = tf.reduce_mean(tf.square(y_target - final_output))
learning_rate = 0.01
model = tf.train.AdamOptimizer(learning_rate).minimize(cost)
init = tf.global_variables_initializer()
sess.run(init)
#Training Loop
loss_vec = []
test_loss = []
epoch = 500
for i in range(epoch):
#generates len(x_val_train) random numbers
rand_index = np.random.choice(len(x_val_train), size = batch_size)
#Get len(x_val_train) data with its 3 input notes or
rand_x = x_val_train[rand_index]
#print(rand_index,rand_x)
rand_y = np.transpose([y_val_train[rand_index]])
sess.run(model, feed_dict = {x_data: rand_x, y_target: rand_y})
temp_loss = sess.run(cost, feed_dict = {x_data: rand_x, y_target : rand_y})
loss_vec.append(np.sqrt(temp_loss))
test_temp_loss = sess.run(cost, feed_dict = {x_data : x_val_test, y_target : np.transpose([y_val_test])})
test_loss.append(np.sqrt(test_temp_loss))
if (i+1)%50!=0:
print('Generation: ' + str(i+1) + '.loss = ' + str(temp_loss))
predict = tf.argmax(tf.add(tf.matmul(hidden_output,A2),b2), 1)
test = np.matrix('2 3 4')
pred = predict.eval(session = sess, feed_dict = {x_data : test})
print("pred: ", pred)
plt.plot(loss_vec, 'k-', label='Train Loss')
plt.plot(test_loss, 'r--', label='Test Loss')
plt.show()
此外，在此代码中， hidden_output = tf.nn.relu（tf.add（tf.matmul（x_data，A1），b1））`
我在规范化数据后成功训练了我的模型。但我需要通过用户输入数据预测输出。
下面，
test = np.matrix('2 3 4')
pred = predict.eval(session = sess, feed_dict = {x_data : test})
print("pred: ", pred)
我已经编写了这段代码来预测结果，但是pred总是返回0.我也尝试了100多个样本，它仍然返回0.你能告诉我哪里出错了吗？
答案 0 :(得分：3)
我们来看看
predict = tf.argmax(tf.add(tf.matmul(hidden_output,A2),b2), 1)
这是（几乎）等于
predict = tf.argmax(final_output)
argmax 是主要问题。如果 final_output 是1热门编码，则 argmax 会有意义，但 final_output 只是一组标量。
如果您有
，这是完整的工作代码import numpy as np
import tensorflow as tf
import os
import urllib
# Data sets
IRIS_TRAINING = "iris_training.csv"
IRIS_TRAINING_URL = "http://download.tensorflow.org/data/iris_training.csv"
IRIS_TEST = "iris_test.csv"
IRIS_TEST_URL = "http://download.tensorflow.org/data/iris_test.csv"
# If the training and test sets aren't stored locally, download them.
if not os.path.exists(IRIS_TRAINING):
raw = urllib.urlopen(IRIS_TRAINING_URL).read()
with open(IRIS_TRAINING, "w") as f:
f.write(raw)
if not os.path.exists(IRIS_TEST):
raw = urllib.urlopen(IRIS_TEST_URL).read()
with open(IRIS_TEST, "w") as f:
f.write(raw)
training_set = tf.contrib.learn.datasets.base.load_csv_with_header( filename=IRIS_TRAINING, target_dtype=np.int, features_dtype=np.float32)
test_set = tf.contrib.learn.datasets.base.load_csv_with_header( filename=IRIS_TEST, target_dtype=np.int, features_dtype=np.float32)
x_val_train = training_set.data[:,:3]
x_val_test = test_set.data[:,:3]
y_val_train = training_set.data[:,3].reshape([-1,1])
y_val_test = test_set.data[:,3].reshape([-1,1])
x_data = tf.placeholder(shape=[None, 3], dtype = tf.float32)
y_target = tf.placeholder(shape = [None, 1], dtype = tf.float32) #Figure out usage of None
#Create Layers for NN
hidden_layer_size = 20
A1 = tf.Variable(tf.random_normal(shape = [3,hidden_layer_size])) #Input -> Hidden
b1 = tf.Variable(tf.random_normal(shape = [hidden_layer_size])) #bias in Input for hidden
A2 = tf.Variable(tf.random_normal(shape = [hidden_layer_size,1])) #Hidden -> Output
b2 = tf.Variable(tf.random_normal(shape = [1])) #Hidden Layer Bias
#Generation of model
hidden_output = tf.nn.relu(tf.add(tf.matmul(x_data,A1),b1))
final_output = tf.add(tf.matmul(hidden_output,A2),b2)
loss = tf.reduce_mean(tf.square(y_target - final_output))
learning_rate = 0.01
train = tf.train.AdamOptimizer(learning_rate).minimize(loss)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
#Training Loop
loss_vec = []
test_loss = []
epoch = 2000
batch_size = 100
def oneTrainingSession(epoch,loss_vec,test_loss,batch_size) :
rand_index = np.random.choice(len(x_val_train), size = batch_size)
rand_x = x_val_train #[rand_index,:]
rand_y = y_val_train #[rand_index,:]
temp_loss,_ = sess.run([loss,train], feed_dict = {x_data: rand_x, y_target : rand_y})
loss_vec.append(np.sqrt(temp_loss))
test_temp_loss = sess.run(loss, feed_dict = {x_data : x_val_test, y_target : y_val_test})
test_loss.append(np.sqrt(test_temp_loss))
if (i+1)%500 == 0:
print('Generation: ' + str(i+1) + '.loss = ' + str(temp_loss))
for i in range(epoch):
oneTrainingSession(epoch,loss_vec,test_loss,batch_size)
test = x_val_test[:3,:]
print "The test values are"
print test
print ""
pred = sess.run(final_output, feed_dict = {x_data : test})
print("pred: ", pred)
Generation: 500.loss = 0.12768
Generation: 1000.loss = 0.0389756
Generation: 1500.loss = 0.0370268
Generation: 2000.loss = 0.0361797
The test values are
[[ 5.9000001 3. 4.19999981]
[ 6.9000001 3.0999999 5.4000001 ]
[ 5.0999999 3.29999995 1.70000005]]
('pred: ', array([[ 1.45187187],
[ 1.92516518],
[ 0.36887735]], dtype=float32))