blocks|key|4374991|text|keras.callbacks.TensorBoard(log_dir='./Graph',+histogram_freq=0,++
++++++++++write_graph=True,+write_images=True)|type|code-block|depth|inlineStyleRanges|entityRanges|data|syntax|javascript|4374992|这一行创建了一个回调Tensorboard对象，您应该捕获该对象并将其提供给模型的fit函数。|unstyled|offset|length|style|CODE|4374993|tbCallBack+=+keras.callbacks.TensorBoard(log_dir='./Graph',+histogram_freq=0,+write_graph=True,+write_images=True)
...
model.fit(...inputs+and+parameters...,+callbacks=[tbCallBack])|4374994|通过这种方式，您可以将回调对象提供给函数。它将在训练期间运行，并将输出可与tensorboard一起使用的文件。|4374995|如果要可视化训练期间创建的文件，请在终端中运行|4374996|tensorboard+--logdir+path_to_current_dir/Graph+|4374997|希望这能有所帮助！|4374998|entityMap^0|0|15|3|0|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|W|8|@]|9|@]|A|$B|C]]|$1|D|3|E|5|F|7|X|8|@$G|Y|H|Z|I|J]]|9|@]|A|$]]|$1|K|3|L|5|6|7|10|8|@]|9|@]|A|$B|C]]|$1|M|3|N|5|F|7|11|8|@]|9|@]|A|$]]|$1|O|3|P|5|F|7|12|8|@]|9|@]|A|$]]|$1|Q|3|R|5|6|7|13|8|@]|9|@]|A|$B|C]]|$1|S|3|T|5|F|7|14|8|@]|9|@]|A|$]]|$1|U|3|-4|5|F|7|15|8|@]|9|@]|A|$]]]|V|$]]

<pre class="lang-py prettyprint-override"><code>keras.callbacks.TensorBoard(log_dir='./Graph', histogram_freq=0, 
 write_graph=True, write_images=True)
</code></pre>

This line creates a Callback Tensorboard object, you should capture that object and give it to the <code>fit</code> function of your model.

<pre class="lang-py prettyprint-override"><code>tbCallBack = keras.callbacks.TensorBoard(log_dir='./Graph', histogram_freq=0, write_graph=True, write_images=True)
...
model.fit(...inputs and parameters..., callbacks=[tbCallBack])
</code></pre>

This way you gave your callback object to the function. It will be run during the training and will output files that can be used with tensorboard.

If you want to visualize the files created during training, run in your terminal

<pre><code>tensorboard --logdir path_to_current_dir/Graph 
</code></pre>

Hope this helps !

blocks|key|4375026|text|变化|type|unstyled|depth|inlineStyleRanges|entityRanges|data|4375027|keras.callbacks.TensorBoard(log_dir='/Graph',+histogram_freq=0,++
++++++++++write_graph=True,+write_images=True)|code-block|syntax|javascript|4375028|至|4375029|tbCallBack+=+keras.callbacks.TensorBoard(log_dir='Graph',+histogram_freq=0,++
++++++++++write_graph=True,+write_images=True)|4375030|并设置您的模型|4375031|tbCallback.set_model(model)|4375032|在你的终端中运行|4375033|tensorboard++--logdir+Graph/|4375034|entityMap^0|0|0|0|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|U|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|V|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|W|8|@]|9|@]|A|$]]|$1|I|3|J|5|D|7|X|8|@]|9|@]|A|$E|F]]|$1|K|3|L|5|6|7|Y|8|@]|9|@]|A|$]]|$1|M|3|N|5|D|7|Z|8|@]|9|@]|A|$E|F]]|$1|O|3|P|5|6|7|10|8|@]|9|@]|A|$]]|$1|Q|3|R|5|D|7|11|8|@]|9|@]|A|$E|F]]|$1|S|3|-4|5|6|7|12|8|@]|9|@]|A|$]]]|T|$]]

Change 

<pre><code>keras.callbacks.TensorBoard(log_dir='/Graph', histogram_freq=0, 
 write_graph=True, write_images=True)
</code></pre>

to

<pre><code>tbCallBack = keras.callbacks.TensorBoard(log_dir='Graph', histogram_freq=0, 
 write_graph=True, write_images=True)
</code></pre>

and set your model

<pre><code>tbCallback.set_model(model)
</code></pre>

Run in your terminal

<pre><code>tensorboard --logdir Graph/
</code></pre>

blocks|key|4375064|text|你写了log_dir='/Graph'，你是指./Graph吗？你当时就把它发给了/home/user/Graph。|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|4375065|entityMap^0|3|G|N|7|15|G|0^^$0|@$1|2|3|4|5|6|7|H|8|@$9|I|A|J|B|C]|$9|K|A|L|B|C]|$9|M|A|N|B|C]]|D|@]|E|$]]|$1|F|3|-4|5|6|7|O|8|@]|D|@]|E|$]]]|G|$]]

You wrote <code>log_dir='/Graph'</code> did you mean <code>./Graph</code> instead? You sent it to <code>/home/user/Graph</code> at the moment.

blocks|key|4375125|text|这就是您使用TensorBoard+callback的方式|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|4375126|from+keras.callbacks+import+TensorBoard

tensorboard+=+TensorBoard(log_dir='./logs',+histogram_freq=0,
++++++++++++++++++++++++++write_graph=True,+write_images=False)
#+define+model
model.fit(X_train,+Y_train,
++++++++++batch_size=batch_size,
++++++++++epochs=nb_epoch,
++++++++++validation_data=(X_test,+Y_test),
++++++++++shuffle=True,
++++++++++callbacks=[tensorboard])|code-block|syntax|javascript|4375127|entityMap|0|LINK|mutability|MUTABLE|url|https://keras.io/callbacks/#tensorboard^0|6|K|0|0|0^^$0|@$1|2|3|4|5|6|7|Q|8|@]|9|@$A|R|B|S|1|T]]|C|$]]|$1|D|3|E|5|F|7|U|8|@]|9|@]|C|$G|H]]|$1|I|3|-4|5|6|7|V|8|@]|9|@]|C|$]]]|J|$K|$5|L|M|N|C|$O|P]]]]

This is how you use the <a href="https://keras.io/callbacks/#tensorboard" rel="noreferrer">TensorBoard callback</a>:

<pre class="lang-py prettyprint-override"><code>from keras.callbacks import TensorBoard

tensorboard = TensorBoard(log_dir='./logs', histogram_freq=0,
 write_graph=True, write_images=False)
# define model
model.fit(X_train, Y_train,
 batch_size=batch_size,
 epochs=nb_epoch,
 validation_data=(X_test, Y_test),
 shuffle=True,
 callbacks=[tensorboard])
</code></pre>

blocks|key|4375714|text|下面是一些代码：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|4375715|K.set_learning_phase(1)
K.set_image_data_format('channels_last')

tb_callback+=+keras.callbacks.TensorBoard(
++++log_dir=log_path,
++++histogram_freq=2,
++++write_graph=True
)
tb_callback.set_model(model)
callbacks+=+[]
callbacks.append(tb_callback)

#+Train+net:
history+=+model.fit(
++++[x_train],
++++[y_train,+y_train_c],
++++batch_size=int(hype_space['batch_size']),
++++epochs=EPOCHS,
++++shuffle=True,
++++verbose=1,
++++callbacks=callbacks,
++++validation_data=([x_test],+[y_test,+y_test_coarse])
).history

#+Test+net:
K.set_learning_phase(0)
score+=+model.evaluate([x_test],+[y_test,+y_test_coarse],+verbose=0)|code-block|syntax|javascript|4375716|基本上，histogram_freq=2是调用此回调时需要调优的最重要的参数:它设置调用回调的时间间隔，目标是在磁盘上生成更少的文件。|offset|length|style|CODE|4375717|这里是在TensorBoard的“直方图”选项卡下看到的在整个训练过程中最后一次卷积的值演变的可视化示例(我发现“分布”选项卡包含非常相似的图表，但翻过来了)：|4375718|​|4375719|📷|atomic|4375720|4375721|如果你想在上下文中看到完整的例子，你可以参考这个开源项目：https://github.com/Vooban/Hyperopt-Keras-CNN-CIFAR-100|4375722|entityMap|0|IMAGE|mutability|IMMUTABLE|imageUrl|https://ask.qcloudimg.com/http-save/yehe-900000/b0491df3e2f4c439ce65d3d32ef90783.png|imageAlt|1|LINK|MUTABLE|url|https://github.com/Vooban/Hyperopt-Keras-CNN-CIFAR-100^0|0|0|4|G|0|0|0|0|1|0|0|0|T|1I|1|0^^$0|@$1|2|3|4|5|6|7|1A|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|1B|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|1C|8|@$I|1D|J|1E|K|L]]|9|@]|A|$]]|$1|M|3|N|5|6|7|1F|8|@]|9|@]|A|$]]|$1|O|3|P|5|6|7|1G|8|@]|9|@]|A|$]]|$1|Q|3|R|5|S|7|1H|8|@]|9|@$I|1I|J|1J|1|1K]]|A|$]]|$1|T|3|P|5|6|7|1L|8|@]|9|@]|A|$]]|$1|U|3|V|5|6|7|1M|8|@]|9|@$I|1N|J|1O|1|1P]]|A|$]]|$1|W|3|-4|5|6|7|1Q|8|@]|9|@]|A|$]]]|X|$Y|$5|Z|10|11|A|$12|13|14|-4]]|15|$5|16|10|17|A|$18|19]]]]

Here is some code: 

<pre class="lang-py prettyprint-override"><code>K.set_learning_phase(1)
K.set_image_data_format('channels_last')

tb_callback = keras.callbacks.TensorBoard(
 log_dir=log_path,
 histogram_freq=2,
 write_graph=True
)
tb_callback.set_model(model)
callbacks = []
callbacks.append(tb_callback)

# Train net:
history = model.fit(
 [x_train],
 [y_train, y_train_c],
 batch_size=int(hype_space['batch_size']),
 epochs=EPOCHS,
 shuffle=True,
 verbose=1,
 callbacks=callbacks,
 validation_data=([x_test], [y_test, y_test_coarse])
).history

# Test net:
K.set_learning_phase(0)
score = model.evaluate([x_test], [y_test, y_test_coarse], verbose=0)
</code></pre>

Basically, <code>histogram_freq=2</code> is the most important parameter to tune when calling this callback: it sets an interval of epochs to call the callback, with the goal of generating fewer files on disks.

So here is an example visualization of the evolution of values for the last convolution throughout training once seen in TensorBoard, under the "histograms" tab (and I found the "distributions" tab to contain very similar charts, but flipped on the side):

<img src="https://raw.githubusercontent.com/Vooban/Hyperopt-Keras-CNN-CIFAR-100/master/tensorboard_histogram_example.png" alt="tensorboard weights monitoring">

In case you would like to see a full example in context, you can refer to this open-source project: <a href="https://github.com/Vooban/Hyperopt-Keras-CNN-CIFAR-100" rel="noreferrer">https://github.com/Vooban/Hyperopt-Keras-CNN-CIFAR-100</a>

blocks|key|4375772|text|你应该看看Losswise+(https://losswise.com)，它有一个Keras插件，比Tensorboard更容易使用，并且有一些很好的额外功能。使用Losswise，你只需要先使用from+losswise.libs+import+LosswiseKerasCallback，然后使用callback+=+LosswiseKerasCallback(tag='my+fancy+convnet+1')，然后就可以运行了(参见https://docs.losswise.com/#keras-plugin)。|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|4375773|entityMap|0|LINK|mutability|MUTABLE|url|https://losswise.com/|1|https://docs.losswise.com/#keras-plugin^0|2Q|1B|46|1M|F|K|0|64|13|1|0^^$0|@$1|2|3|4|5|6|7|P|8|@$9|Q|A|R|B|C]|$9|S|A|T|B|C]]|D|@$9|U|A|V|1|W]|$9|X|A|Y|1|Z]]|E|$]]|$1|F|3|-4|5|6|7|10|8|@]|D|@]|E|$]]]|G|$H|$5|I|J|K|E|$L|M]]|N|$5|I|J|K|E|$L|O]]]]

You should check out Losswise (<a href="https://losswise.com" rel="nofollow noreferrer">https://losswise.com</a>), it has a plugin for Keras that's easier to use than Tensorboard and has some nice extra features. With Losswise you'd just use <code>from losswise.libs import LosswiseKerasCallback</code> and then <code>callback = LosswiseKerasCallback(tag='my fancy convnet 1')</code> and you're good to go (see <a href="https://docs.losswise.com/#keras-plugin" rel="nofollow noreferrer">https://docs.losswise.com/#keras-plugin</a>).

blocks|key|4375841|text|有很少的东西。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|4375842|首先，不是/Graph而是./Graph|offset|length|style|CODE|4375843|其次，当您使用TensorBoard回调时，一定要传递验证数据，因为没有它，它就不会启动。|4375844|第三，如果您想使用除标量汇总之外的任何东西，那么您应该只使用fit方法，因为fit_generator将不起作用。或者，您可以重写回调以使用fit_generator。|4375845|要添加回调，只需将其添加到model.fit(...,+callbacks=your_list_of_callbacks)|4375846|entityMap^0|0|5|6|D|7|0|0|U|3|12|D|1Y|D|0|D|1C|0^^$0|@$1|2|3|4|5|6|7|P|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|Q|8|@$D|R|E|S|F|G]|$D|T|E|U|F|G]]|9|@]|A|$]]|$1|H|3|I|5|6|7|V|8|@]|9|@]|A|$]]|$1|J|3|K|5|6|7|W|8|@$D|X|E|Y|F|G]|$D|Z|E|10|F|G]|$D|11|E|12|F|G]]|9|@]|A|$]]|$1|L|3|M|5|6|7|13|8|@$D|14|E|15|F|G]]|9|@]|A|$]]|$1|N|3|-4|5|6|7|16|8|@]|9|@]|A|$]]]|O|$]]

There are few things.

First, not <code>/Graph</code> but <code>./Graph</code>

Second, when you use the TensorBoard callback, always pass validation data, because without it, it wouldn't start.

Third, if you want to use anything except scalar summaries, then you should only use the <code>fit</code> method because <code>fit_generator</code> will not work. Or you can rewrite the callback to work with <code>fit_generator</code>.

To add callbacks, just add it to <code>model.fit(..., callbacks=your_list_of_callbacks)</code>

blocks|key|4375480|text|如果您正在使用Keras库，并希望使用tensorboard打印精确度和其他变量的图形，那么以下是要遵循的步骤。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|4375481|Step1:使用以下命令初始化keras回调库导入tensorboard|4375482|from+keras.callbacks+import+TensorBoard|code-block|syntax|javascript|4375483|步骤2:在你的程序中将下面的命令放在"model.fit()“命令之前。|4375484|tensor_board+=+TensorBoard(log_dir='./Graph',+histogram_freq=0,+write_graph=True,+write_images=True)|4375485|注意:使用"./graph“。它将在您当前的工作目录中生成图形文件夹，避免使用"/graph“。|4375486|步骤3:在"model.fit()".The示例中包含Tensorboard回调如下所示。|4375487|model.fit(X_train,y_train,+batch_size=batch_size,+epochs=nb_epoch,+verbose=1,+validation_split=0.2,callbacks=[tensor_board])|4375488|步骤4:运行您的代码并检查您的图形文件夹是否在您的工作目录中。如果上述代码工作正常，您的工作目录中将会有"Graph“文件夹。|4375489|步骤5:在您的工作目录中打开终端，然后键入以下命令。|4375490|tensorboard+--logdir+./Graph|4375491|步骤6:现在打开您的web浏览器，并在下面输入地址。|4375492|http://localhost:6006|4375493|进入后，Tensorbaord页面将打开，您可以在其中看到不同变量的图形。|4375494|entityMap^0|0|0|0|0|0|0|0|0|0|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|16|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|17|8|@]|9|@]|A|$]]|$1|D|3|E|5|F|7|18|8|@]|9|@]|A|$G|H]]|$1|I|3|J|5|6|7|19|8|@]|9|@]|A|$]]|$1|K|3|L|5|F|7|1A|8|@]|9|@]|A|$G|H]]|$1|M|3|N|5|6|7|1B|8|@]|9|@]|A|$]]|$1|O|3|P|5|6|7|1C|8|@]|9|@]|A|$]]|$1|Q|3|R|5|F|7|1D|8|@]|9|@]|A|$G|H]]|$1|S|3|T|5|6|7|1E|8|@]|9|@]|A|$]]|$1|U|3|V|5|6|7|1F|8|@]|9|@]|A|$]]|$1|W|3|X|5|F|7|1G|8|@]|9|@]|A|$G|H]]|$1|Y|3|Z|5|6|7|1H|8|@]|9|@]|A|$]]|$1|10|3|11|5|F|7|1I|8|@]|9|@]|A|$G|H]]|$1|12|3|13|5|6|7|1J|8|@]|9|@]|A|$]]|$1|14|3|-4|5|6|7|1K|8|@]|9|@]|A|$]]]|15|$]]

If you are working with Keras library and want to use tensorboard to print your graphs of accuracy and other variables, Then below are the steps to follow.

step 1: Initialize the keras callback library to import tensorboard by using below command 

<pre><code>from keras.callbacks import TensorBoard
</code></pre>

step 2: Include the below command in your program just before "model.fit()" command. 

<pre><code>tensor_board = TensorBoard(log_dir='./Graph', histogram_freq=0, write_graph=True, write_images=True)
</code></pre>

Note: Use "./graph". It will generate the graph folder in your current working directory, avoid using "/graph".

step 3: Include Tensorboard callback in "model.fit()".The sample is given below.

<pre><code>model.fit(X_train,y_train, batch_size=batch_size, epochs=nb_epoch, verbose=1, validation_split=0.2,callbacks=[tensor_board])
</code></pre>

step 4 : Run your code and check whether your graph folder is there in your working directory. if the above codes work correctly you will have "Graph"
folder in your working directory.

step 5 : Open Terminal in your working directory and type the command below.

<pre><code>tensorboard --logdir ./Graph
</code></pre>

step 6: Now open your web browser and enter the address below.

<pre><code>http://localhost:6006
</code></pre>

After entering, the Tensorbaord page will open where you can see your graphs of different variables.

I have built a neural network with Keras. I would visualize its data by Tensorboard, therefore I have utilized:

<pre class="lang-py prettyprint-override"><code>keras.callbacks.TensorBoard(log_dir='/Graph', histogram_freq=0,
 write_graph=True, write_images=True)
</code></pre>

as explained in <a href="https://keras.io/callbacks/#tensorboard" rel="noreferrer">keras.io</a>. When I run the callback I get <code>&lt;keras.callbacks.TensorBoard at 0x7f9abb3898&gt;</code>, but I don't get any file in my folder "Graph". Is there something wrong in how I have used this callback?

How do I use the Tensorboard callback of Keras?

我已经用Keras建立了一个神经网络。我会通过Tensorboard可视化它的数据，因此我利用了：keras.callbacks.TensorBoard(log_dir='/Graph', histogram_freq=0,                            write_graph=True, wr...

问如何使用Keras的Tensorboard回调？
EN

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问如何使用Keras的Tensorboard回调？EN

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问如何使用Keras的Tensorboard回调？
EN