爲什麼我在這個神經網絡（tensorflow）中得到低精度？

Question

我與tensorflow卷積神經網絡，我訓練它，測試它（約98％的準確率）...我保存

saver = tf.train.Saver() 
saver.save(sess, 'model.ckpt') 

那麼模型我金丹恢復，但我總是得到低於50％的準確度......爲什麼？ 下面的代碼：

import tensorflow as tf 
import matplotlib.pyplot as plt 
import pickle 
import numpy as np 

with open('X_train.pickle', 'rb') as y: 
    u = pickle._Unpickler(y) 
    u.encoding = 'latin1' 
    X_train = u.load() 

with open('X_test.pickle', 'rb') as y: 
    u = pickle._Unpickler(y) 
    u.encoding = 'latin1' 
    X_test = u.load() 
    X_test = np.array(X_test).reshape(-1, 2500) 

with open('y_train.pickle', 'rb') as y: 
    u = pickle._Unpickler(y) 
    u.encoding = 'latin1' 
    y_train = u.load() 

with open('y_test.pickle', 'rb') as y: 
    u = pickle._Unpickler(y) 
    u.encoding = 'latin1' 
    y_test = u.load() 

n_classes = 3 
batch_size = 100 

x = tf.placeholder('float', [None, 2500]) 
y = tf.placeholder('float') 

keep_rate = 0.8 
keep_prob = tf.placeholder(tf.float32) 

def conv2d(x, W): 
    return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME') 

def maxpool2d(x): 
    #      size of window   movement of window 
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME') 



def convolutional_neural_network(x): 
    weights = {'W_conv1':tf.Variable(tf.random_normal([5,5,1,32])), 
       'W_conv2':tf.Variable(tf.random_normal([5,5,32,64])), 
       'W_fc':tf.Variable(tf.random_normal([13*13*64,1024])), 
       'out':tf.Variable(tf.random_normal([1024, n_classes]))} 

    biases = {'b_conv1':tf.Variable(tf.random_normal([32])), 
       'b_conv2':tf.Variable(tf.random_normal([64])), 
       'b_fc':tf.Variable(tf.random_normal([1024])), 
       'out':tf.Variable(tf.random_normal([n_classes]))} 

    x = tf.reshape(x, shape=[-1, 50, 50, 1]) 

    conv1 = tf.nn.relu(conv2d(x, weights['W_conv1']) + biases['b_conv1']) 
    conv1 = maxpool2d(conv1) 

    conv2 = tf.nn.relu(conv2d(conv1, weights['W_conv2']) + biases['b_conv2']) 
    conv2 = maxpool2d(conv2) 

    fc = tf.reshape(conv2,[-1, 13*13*64]) 
    fc = tf.nn.relu(tf.matmul(fc, weights['W_fc'])+biases['b_fc']) 
    #fc = tf.nn.dropout(fc, keep_rate) 

    output = tf.matmul(fc, weights['out'])+biases['out'] 

    return output 


def use_neural_network(input_data): 
    prediction = convolutional_neural_network(x) 
    sess.run(tf.global_variables_initializer()) 

    result = (sess.run(tf.argmax(prediction.eval(feed_dict={x:[input_data]}),1))) 

    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})) 

    return result 

with tf.Session() as sess: 

    c = convolutional_neural_network(x) 
    saver = tf.train.Saver() 
    saver.restore(sess, "model.ckpt") 

    sample = X_train[432].reshape(2500) 
    res = use_neural_network(sample) 

    if res == [0]: print('Go straight') 
    elif res == [1]: print('Turn right') 
    else: print('Turn left') 

    img = sample.reshape(50,50) 
    plt.imshow(img) 
    plt.show() 

    sample = X_train[1222].reshape(2500) 
    res = use_neural_network(sample) 

    if res == [0]: print('Go straight') 
    elif res == [1]: print('Turn right') 
    else: print('Turn left') 

    img = sample.reshape(50,50) 
    plt.imshow(img) 
    plt.show() 


    sample = X_train[2986].reshape(2500) 
    res = use_neural_network(sample) 

    if res == [0]: print('Go straight') 
    elif res == [1]: print('Turn right') 
    else: print('Turn left') 

    img = sample.reshape(50,50) 
    plt.imshow(img) 
    plt.show() 

的問題不能過學習，因爲我與訓練數據集的元素測試它... 我敢肯定，這個問題是金丹，但我無法弄清楚如何解決它...

Answer 1

當你使用tensorlfow來訓練一個模型時，確保你使用的是tensorflow版本1.0和以上的。一旦你使用最新版本文件訓練模型將創建命名如下：

1. MODELNAME。 data

   這是TensorBundle集合，保存所有變量的值。

2. modelname。 索引

   .index存儲變量名稱和形狀保存的列表。

3. modelname。 meta

   此文件描述保存的圖形結構，包括GraphDef，SaverDef等。

要重新載入/恢復模型中使用model.load（MODELNAME）它不僅載入你的模型，而且精度也不會忽高忽低。

注：請使用TFLearn，TFLearn引入了高級API，使神經網絡的建設和培訓，快速和容易。欲瞭解更多詳情，請登錄http://tflearn.org/getting_started/

建築的簡單，通用的方法和使用CNN使用tensorflow如下：

構建網絡：

Here your will create n convolution , max-poll layer and fully connected layer then apply whatever activation function you want and return your model object 

火車模型：

fit your training data into your model using model.fit(X,Y) 

保存模型：

Save your model using model.save(modelName) 

刷新型號：

Reload your model using model.load(modelName) 

這是建立和使用CNN通用和簡化的方式。

希望它可以幫助你:)