tensorflow多标签分类mnis

Question

我正在尝试对mnist数据集执行序列检测。 我想在没有RNN的情况下做这件事。 为了做到这一点，我水平堆叠（最多）5个图像序列，然后运行它的分类。 然而，它不工作，以及我收到低精度

data = tf.placeholder(dtype=tf.float32,shape=(None, 28,140,1))
tf_train_labels = tf.placeholder(dtype=tf.float32, shape=(None, 5,11))

w1 = tf.Variable(tf.truncated_normal(shape=(3,3, 1,32), stddev=0.1))
b1 = tf.Variable(tf.zeros(32))

w2 = tf.Variable(tf.truncated_normal(shape=(3,3,32,64), stddev=0.1))
b2 = tf.Variable(tf.constant(1., shape=[64]))

w22 = tf.Variable(tf.truncated_normal(shape=(3,3,64,128), stddev=0.1))
b22 = tf.Variable(tf.constant(1., shape=[128]))



w3 = tf.Variable(tf.truncated_normal(shape=(28 // 4 * 140 // 4 * 128,1024)))
b3 = tf.Variable(tf.constant(1., shape=[1024]))

w4 = tf.Variable(tf.truncated_normal(shape=(1024,11), stddev=0.1))
b4 = tf.Variable(tf.constant(1., shape=[11]))

w5 = tf.Variable(tf.truncated_normal(shape=(1024,11), stddev=0.1))
b5 = tf.Variable(tf.constant(1., shape=[11]))

w6 = tf.Variable(tf.truncated_normal(shape=(1024,11), stddev=0.1))
b6 = tf.Variable(tf.constant(1., shape=[11]))

w7 = tf.Variable(tf.truncated_normal(shape=(1024,11), stddev=0.1))
b7 = tf.Variable(tf.constant(1., shape=[11]))

w8 = tf.Variable(tf.truncated_normal(shape=(1024,11), stddev=0.1))
b8 = tf.Variable(tf.constant(1., shape=[11]))



def model(x, w, b):
    conv= tf.nn.relu(tf.nn.conv2d(x, w1, [1,1,1,1], padding="SAME")+b1)
    conv = tf.nn.max_pool(conv, [1,2,2,1], [1,2,2,1], padding="SAME")
    conv = tf.nn.relu(tf.nn.conv2d(conv, w2, [1,1,1,1], padding="SAME")+b2)
    conv = tf.nn.max_pool(conv, [1,2,2,1], [1,2,2,1],padding="SAME")
    conv = tf.nn.relu(tf.nn.conv2d(conv, w22, [1,1,1,1], padding="SAME")+b22)

    shape = conv.get_shape().as_list()
    reshape = tf.reshape(conv, [-1, shape[1] * shape[2] * shape[3]])
    dense = tf.nn.relu(tf.matmul(reshape, w3)+b3)
    return tf.matmul(dense, w) + b
pred1 = model(data, w4, b4)
pred2 = model(data, w5, b5)
pred3 = model(data, w6, b6)
pred4 = model(data, w7, b7)
pred5 = model(data, w8, b8)

prediction = tf.stack([
        tf.nn.softmax(pred1),
        tf.nn.softmax(pred2),
        tf.nn.softmax(pred3),
        tf.nn.softmax(pred4),
        tf.nn.softmax(pred5)])


loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
               logits = pred1, labels = tf_train_labels[:, 0])) + \
           tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
               logits = pred2, labels = tf_train_labels[:, 1])) + \
           tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
               logits = pred3, labels = tf_train_labels[:, 2])) + \
           tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
               logits = pred4, labels = tf_train_labels[:, 3])) + \
           tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
               logits = pred5, labels = tf_train_labels[:, 4]))


optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.0001).minimize(loss)
init = tf.global_variables_initializer()

代码中是否有任何逻辑错误，或者我只是训练时间不够长，或者选择了错误的模型？ 谢谢并致以最诚挚的问候

Answer 1

我通过从梯度下降切换到Adam优化器解决了这个问题