tensorflow - 使用 Tensorflow 的 CNN 模型

Question

我正在通过在 Tensorflow 中构建卷积神经网络模型来进行字符识别。我的模型有 2 个 Conv 层，后面跟着 2 个全连接层。我有大约 78K 训练图像和 13K 测试图像。当我执行模型时，我在测试集上获得了大约 92.xx% 的准确率。当我在 Tensorboard 上可视化我的准确性和损失曲线时。我得到了一条垂直线，但我不知道为什么会得到这个？我得到这样的曲线Accuracy and Cross Entropy curve when viewed on tensorboard 。

权重和偏差的分布曲线也显示一条垂直线 Left side shows testing parameters (weights and bias) and right side shows training parameters on first conv layer

非常感谢在这方面的任何帮助。 !!

def conv_layer(input, size_in, size_out, name="conv"):
with tf.name_scope(name):
w = tf.Variable(tf.random_normal([5, 5, size_in, size_out], stddev=0.1), name="W")
b = tf.Variable(tf.constant(0.1, shape=[size_out]), name="B")
conv = tf.nn.conv2d(input, w, strides=[1, 1, 1, 1],padding="VALID")
act = tf.nn.relu(conv + b)
tf.summary.histogram("weights", w)
tf.summary.histogram("biases", b)
tf.summary.histogram("activations", act)
return tf.nn.max_pool(act, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME")`

def fc_layer(input, size_in, size_out, name="fc"):
with tf.name_scope(name):
w = tf.Variable(tf.random_normal([size_in, size_out], stddev=0.1), name="W")  # Truncated_normal
b = tf.Variable(tf.constant(0.1, shape=[size_out]), name="B")
act = tf.matmul(input, w) + b
tf.summary.histogram("weights", w)
tf.summary.histogram("biases", b)
tf.summary.histogram("activations", act)
return act

def model(use_two_conv, use_two_fc):
sess = tf.Session()
x = tf.placeholder(tf.float32, shape=[None, 1024], name="x")
x_image = tf.reshape(x, [-1, 32, 32, 1])
tf.summary.image('input', x_image, 3)
y = tf.placeholder(tf.float32, shape=[None,46], name="labels")

if use_two_conv:
  conv1 = conv_layer(x_image, 1, 4, "conv1")
  conv_out = conv_layer(conv1,4,16,"conv2")    
else:
  conv1 = conv_layer(x_image, 1, 16, "conv1")
  conv_out = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME")

flattened = tf.reshape(conv_out, [-1, 5 * 5 * 16])

if use_two_fc:
  fc1 = fc_layer(flattened, 5 * 5 * 16, 200, "fc1")
  relu = tf.nn.relu(fc1)
  tf.summary.histogram("fc1/relu", relu)
  logits = fc_layer(fc1, 200, 46, "fc2")        

else:
  logits = fc_layer(flattened, 5*5*16, 46, "fc")  

Answer 1

当我过去遇到这个问题时，这是使用的结果

writer.add_summary(current_summary)

而不是

writer.add_summary(current_summary, epoch)

(使用通用变量名称，因为询问者代码的相关部分未发布。)例如，

summary_op = tf.summary.merge_all()
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    writer = tf.summary.FileWriter("/Whatever/Path", sess.graph)
    for iteration in range(1001):
        if epoch % 100 == 0:
            _, current_summary = sess.run([training_op, summary_op])
            writer.add_summary(current_summary, iteration)
        else:
            _ = sess.run(training_op)