Python 张力板不显示任何内容

我对张力板有问题。我的代码运行良好，当我尝试使用tensorboard--logdir=logs/log1可视化图形，然后打开浏览器，键入localhost:6006时，我看到了没有内容的页面（只有tensorboard符号和选项卡，如事件、图形…） 非常感谢你的帮助。不知道如何解决这个问题。 （我正在使用jupyter笔记本）

以下是我收到的错误消息：

WARNING:tensorflow:IOError [Errno 2] No such file or directory:       '/home/tiger/anaconda3/envs/tensorflow/lib/python3.5/site-   packages/tensorflow/tensorboard/TAG' on path /home/tiger/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/tensorboard/TAG
WARNING:tensorflow:Unable to read TensorBoard tag
Starting TensorBoard  on port 6006
(You can navigate to http://0.0.0.0:6006)
127.0.0.1 - - [03/Jun/2016 21:20:49] "GET / HTTP/1.1" 200 -
WARNING:tensorflow:IOError [Errno 2] No such file or directory: '/home/tiger/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/tensorboard/lib/css/global.css' on path /home/tiger/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/tensorboard/lib/css/global.css
127.0.0.1 - - [03/Jun/2016 21:20:49] code 404, message Not Found
127.0.0.1 - - [03/Jun/2016 21:20:49] "GET /lib/css/global.css HTTP/1.1" 404 -
127.0.0.1 - - [03/Jun/2016 21:20:50] "GET /external/lodash/lodash.min.js HTTP/1.1" 200 -
.......
WARNING:tensorflow:IOError [Errno 2] No such file or directory: '/home/tiger/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/tensorboard/favicon.ico' on path /home/tiger/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/tensorboard/favicon.ico

我的代码如下：

n_features = x_train.shape[1]
n_samples = x_train.shape[0]
n_labels = 10
n_hidden = 200
epoch_train = 200
learning_rate = 0.01
batch_size = 20

x_tr = tf.placeholder(tf.float32, shape=(None, n_features), name='x')
y_tr = tf.placeholder(tf.float32, shape=(None, n_labels), name='y')

w1 = tf.Variable(tf.truncated_normal([n_features,n_hidden]),name='weight1')
b1 = tf.Variable (tf.zeros([n_hidden]), name='bias1')
w2 = tf.Variable (tf.truncated_normal([n_hidden, n_labels]),name ='weight2')
b2 = tf.Variable(tf.zeros([n_labels]), name='bias2')

w1_hist = tf.histogram_summary('weight1', w1)
w2_hist = tf.histogram_summary('weight2', w2)
b1_hist = tf.histogram_summary('bias1', b1)
b2_hist = tf.histogram_summary('bias2', b2)
y_hist = tf.histogram_summary('y', y_tr)

with tf.name_scope('hidden') as scope:    
    z1 = tf.matmul(x_tr, w1)+b1
    a1 = tf.nn.relu (z1)

with tf.name_scope('output') as scope:    
    z2 = tf.matmul(a1, w2)+b2
    a2 = tf.nn.softmax (z2)

with tf.name_scope('cost') as scope:
    loss = tf.reduce_mean (tf.nn.softmax_cross_entropy_with_logits(z2, y_tr))
    cost_summ = tf.scalar_summary ('cost', loss)

with tf.name_scope('train') as scope:
    optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss)

def acc (pred, y):
     return (np.mean(np.argmax(pred, 1)==np.argmax(y,1)))


with tf.Session() as session:

session.run(tf.initialize_all_variables())

merged = tf.merge_summary([y_hist, w1_hist, w2_hist, b1_hist, b2_hist, cost_summ])
writer = tf.train.SummaryWriter ('logs/log1', session.graph)

for epoch in range (epoch_train):

    offset = epoch*batch_size % (x_train.shape[0]-batch_size)
    x_tr_batch = x_train[offset:offset+batch_size, :]
    y_tr_batch = y_train[offset:offset+batch_size, :]
    feed_dict = {x_tr:x_tr_batch, y_tr:y_tr_batch}

    _, cost, prediction = session.run ([optimizer, loss, a2], feed_dict=feed_dict)

    summary = session.run (merged, feed_dict=feed_dict)
    writer.add_summary(summary,epoch)

    if epoch % 20 ==0:
        print ('training accuracy:', acc(prediction, y_tr_batch))
        print ('cost at epoch {} is:'.format(epoch), cost)
pred_ts = session.run (a2, feed_dict = {x_tr:x_test})
print ('test accuracy is:', acc(pred_ts, y_test))

---

看起来这个问题和你的工作有关。确保在运行程序后启动tensorboard。还要看看其他人是怎么解决的。可能是张力板上的一只虫子。是否要从源代码构建tensorflow？

您得到的错误不会困扰我。我想问题是你什么都没写。您可以尝试在

add_summary（）

行之后添加此行

writer.flush（）

，如果您确实看到选项卡，但没有看到选项卡“嵌入”，则可能是旧版本的tensorflow/tensorboard。尝试升级到1.0，这对我很有用

您可以通过编写以下命令来访问张力板： tensorboard--logdir=“您的模型临时目录”-host=127.0.0.1

现在在浏览器中打开127.0.0.1:6006，将在张力板上显示内容。

---

我希望这能解决您的问题。

在链接上的一篇帖子之后，我下载了global.css文件，并将其放在错误消息中显示的文件夹中。现在张力板不是完全空白的。它显示类似“未找到xxxx数据”的消息。在我看来，tensor board似乎无法定位或读取事件文件。（我检查了日志文件夹，文件在那里）我两周前刚在我的anaconda Python 3.5上安装了tensorflow。我刚刚试过。相同错误警告：tensorflow:IOError[Errno 2]没有这样的文件或目录：'/home/tiger/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/tensorboard/TAG'路径/home/tiger/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorboard/TAG警告：tensorflow:无法读取tensorboard标记我检查了文件夹。事件文件就在那里。太令人沮丧了…对不起，你能把你称为tensorboard的命令粘贴到这里吗？在你的问题中，在“=”周围似乎有两个空格。你以前遇到的错误发生在我身上，结果仍然显示出来，所以我认为它们是无害的。升级到0.8后，错误就消失了。但是否有任何与logdir路径相关的错误消息？问题已解决。我删除了“=”周围的两个空格，然后它就工作了。虽然我仍然收到错误消息，非常感谢！对不起，迟了答复。刚刚度假回来，谢谢魏唐！在上面的代码中：将tf.Session（）作为Session:以下行不缩进看起来像是for循环结束之前的所有行都必须缩进到该行之后