Tensorflow Nueral Network無法正常工作

Question

感謝您考慮回答我的問題。我有使用TensorFlow一個問題，這是我輸入我的數據，我不斷收到輸出：

('Epoch ', 0, ' completed out of ', 10, 'loss:', nan) 
('Epoch ', 1, ' completed out of ', 10, 'loss:', nan) 
('Epoch ', 2, ' completed out of ', 10, 'loss:', nan) 
('Epoch ', 3, ' completed out of ', 10, 'loss:', nan) 
('Epoch ', 4, ' completed out of ', 10, 'loss:', nan) 
('Epoch ', 5, ' completed out of ', 10, 'loss:', nan) 
('Epoch ', 6, ' completed out of ', 10, 'loss:', nan) 
('Epoch ', 7, ' completed out of ', 10, 'loss:', nan) 
('Epoch ', 8, ' completed out of ', 10, 'loss:', nan) 
('Epoch ', 9, ' completed out of ', 10, 'loss:', nan) 
('Accuracy:', 1.0) 

我X_train數據是500 1000矩陣，其中每行包含數字，如：

-0.38484444, 1.4542222222 ... 

我希望你明白... 而我的Y_train數據由二進制分類（0,1）組成。 len（X_train [0]）返回1000，這是樣本數量（列）

我不太清楚還有什麼需要澄清我的問題;我將包括我簡單的TensorFlow代碼，如果您需要關於我的代碼或問題的更多說明，請告訴我。

謝謝您的時間

import tensorflow as tf 
import pandas as pd 
import numpy as np 

da = pd.read_csv("data.csv", header=None) 
ta = pd.read_csv("BMI.csv") 

X_data = da.iloc[:, :1000] 
Y_data = np.expand_dims(ta.iloc[:, -1], axis = 1) 

X_train = X_data.iloc[:500 :,] 
X_test = X_data.iloc[500:,:] 

Y_train = Y_data[:500 :,] 
Y_test = Y_data[735:,:] 


X_train = np.array(X_train) 
X_test = np.array(X_test) 

n_nodes_hl1 = 500 
n_nodes_hl2 = 500 
n_nodes_hl3 = 500 

n_classes = 1 
batch_size = 10 

x = tf.placeholder('float', [None, len(X_train[0])]) 
y = tf.placeholder('float') 

def neural_network_model(data): 
    hidden_1_layer = {'weights': tf.Variable(tf.random_normal([len(X_train[0]), n_nodes_hl1])), 
         'biases': tf.Variable(tf.random_normal([n_nodes_hl1]))} 
    hidden_2_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])), 
         'biases': tf.Variable(tf.random_normal([n_nodes_hl2]))} 
    hidden_3_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])), 
         'biases': tf.Variable(tf.random_normal([n_nodes_hl3]))} 
    output_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])), 
         'biases': tf.Variable(tf.random_normal([n_classes]))} 

    l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']), hidden_1_layer['biases']) 
    l1 = tf.nn.relu(l1) 

    l2 = tf.add(tf.matmul(l1, hidden_2_layer['weights']), hidden_2_layer['biases']) 
    l2 = tf.nn.relu(l2) 

    l3 = tf.add(tf.matmul(l2, hidden_3_layer['weights']), hidden_3_layer['biases']) 
    l3 = tf.nn.relu(l3) 

    output = tf.matmul(l3, output_layer['weights']) + output_layer['biases'] 

    return output 


def train_nueral_network(x): 
    prediction = neural_network_model(x) 
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y)) 
    optimizer = tf.train.AdamOptimizer().minimize(cost) 

    hm_epochs = 10 

    with tf.Session() as sess: 
     sess.run(tf.global_variables_initializer()) 

     for epoch in range(hm_epochs): 
      epoch_loss = 0 

      i = 0 
      while i < len(X_train[0]): 
       start = i 
       end = i + batch_size 

       batch_x = np.array(X_train[start:end]) 
       batch_y = np.array(Y_train[start:end]) 

       _, c = sess.run([optimizer, cost], feed_dict= {x: batch_x, y: batch_y}) 
       epoch_loss += c 
       i += batch_size 


      print('Epoch ', epoch, ' completed out of ', hm_epochs, 'loss:', epoch_loss) 

     correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1)) 
     accuracy = tf.reduce_mean(tf.cast(correct, 'float')) 
     print('Accuracy:', accuracy.eval({x:X_test, y:Y_test})) 


train_nueral_network(x) 

Answer 1

您可以替換tf.nn.tanh的tf.nn.relu並重新訓練它，並檢查您是否會得到相同的結果。有時候，ReLU會導致消失的梯度問題。

https://ayearofai.com/rohan-4-the-vanishing-gradient-problem-ec68f76ffb9b

Answer 2

你n_classes=1。因此，您可以將softmax應用於單個神經元上，該神經元應始終評估爲1.您應設置n_classes=2。

此外，在當前的設置，您使用的精度評估將永遠是100％正確的：

correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1)) 

這是因爲這兩個prediction和y是形狀(BATCH_SIZE,1)這麼argmax總是會導致爲0所有樣品。

我會建議在一個熱表示代表y。一旦你這樣做了，你的其他代碼就可以工作了。