当使用具有单个输出神经元张量流的神经网络时,损失和准确度为0

时间:2017-08-02 11:02:34

标签: python tensorflow loss

我正在编写一个二元分类器,对于某个任务,而不是在输出层中使用2个神经元,我想只使用一个带有sigmoid函数,并且如果它低于0.5则基本上输出0,否则输出1。

加载图像,调整大小为64x64并展平,以创建问题的传真)。数据加载的代码将在最后出现。我创建了占位符。

x = tf.placeholder('float',[None, 64*64])
y = tf.placeholder('float',[None, 1])

并按如下方式定义模型。

def create_model_linear(data):

    fcl1_desc = {'weights': weight_variable([4096,128]), 'biases': bias_variable([128])}
    fcl2_desc = {'weights': weight_variable([128,1]), 'biases': bias_variable([1])}

    fc1 = tf.nn.relu(tf.matmul(data, fcl1_desc['weights']) + fcl1_desc['biases'])
    fc2 = tf.nn.sigmoid(tf.matmul(fc1, fcl2_desc['weights']) + fcl2_desc['biases'])

    return fc2

函数weight_variablebias_variable只返回给定形状的tf.Variable()。 (他们的代码也在最后。)

然后我定义训练功能如下。

def train(x, hm_epochs):
    prediction = create_model_linear(x)
    cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits  = prediction, labels = y) )
    optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
    batch_size = 100
    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(train_x):
                start = i
                end = i + batch_size
                batch_x = train_x[start:end]
                batch_y = train_y[start:end]
                _, c = sess.run([optimizer, cost], feed_dict = {x:batch_x, y:batch_y})

                epoch_loss += c
                i+=batch_size

            print('Epoch', epoch+1, 'completed out of', hm_epochs,'loss:',epoch_loss)
        correct = tf.greater(prediction,[0.5])
        accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
        i = 0
        acc = []
        while i < len(train_x):
            acc +=[accuracy.eval({x:train_x[i:i+1000], y:train_y[i:i + 1000]})]
            i+=1000
    print sum(acc)/len(acc)

train(x, 10)的输出是

  

('Epoch',1,'完成',10,'损失:',0.0)   ('Epoch',2,'完成',10,'损失:',0.0)   ('Epoch',3,'完成',10,'损失:',0.0)   ('Epoch',4,'完成',10,'损失:',0.0)   ('Epoch',5,'完成',10,'损失:',0.0)   ('Epoch',6,'完成',10,'损失:',0.0)   ('Epoch',7,'完成',10,'损失:',0.0)   ('Epoch',8,'完成',10,'损失:',0.0)   ('Epoch',9,'完成',10,'损失:',0.0)   ('Epoch',10,'完成',10,'损失:',0.0)

     

0.0   我错过了什么?

以下是所有实用程序函数的承诺代码:

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def getLabel(wordlabel):
    if wordlabel == 'Class_A':
        return [1]
    elif wordlabel == 'Class_B':
        return [0]
    else:
        return -1

def loadImages(pathToImgs):
    images = []
    labels = []
    filenames = os.listdir(pathToImgs)
    imgCount = 0
    for i in tqdm(filenames): 
        wordlabel = i.split('_')[1]
        oneHotLabel = getLabel(wordlabel)
        img = cv2.imread(pathToImgs + i,cv2.IMREAD_GRAYSCALE)
        if oneHotLabel != -1 and type(img) is np.ndarray: 
            images += [cv2.resize(img,(64,64)).flatten()]
            labels += [oneHotLabel]
            imgCount+=1
    print imgCount
    return (images,labels)

1 个答案:

答案 0 :(得分:1)

我认为你应该使用tf.nn.sigmoid_cross_entropy_with_logits代替tf.nn.softmax_cross_entropy_with_logits,因为你在输出层使用了sigmoid和1个神经元。

您还需要从create_model_linear中的最后一层移除sigmoid 并且,您未使用y标签,准确性必须符合以下格式。

correct = tf.equal(tf.greater(tf.nn.sigmoid(prediction),[0.5]),tf.cast(y,'bool'))