本文介绍了构造Keras Tensorboard图的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！
问题描述
当我创建一个简单的Keras模型时
When I create a simple Keras Model
model = Sequential()
model.add(Dense(10, activation='tanh', input_dim=1))
model.add(Dense(1, activation='linear'))
model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mean_squared_error'])
并回调到Tensorboard
and do a callback to Tensorboard
tensorboard = TensorBoard(log_dir='c:/temp/tensorboard/run1', histogram_freq=1, write_graph=True, write_images=False)
model.fit(x, y, epochs=1000, batch_size=1, callbacks=[tensorboard])
Tensorboard中的输出如下所示:
The output in Tensorboard looks like this:
换句话说，这是一团糟.
In other words, it's a complete mess.
- 有什么我可以做的使图形输出看起来更有条理吗?
- 如何使用Keras和Tensorboard创建权重的直方图?
推荐答案
您可以使用K.name_scope('name_scope')创建名称范围以对模型中的图层进行分组.
You can create a name scope to group layers in your model using with K.name_scope('name_scope').
示例:
with K.name_scope('CustomLayer'):
# add first layer in new scope
x = GlobalAveragePooling2D()(x)
# add a second fully connected layer
x = Dense(1024, activation='relu')(x)
感谢 https://github.com/fchollet/keras/pull/4233#issuecomment-316954784
这篇关于构造Keras Tensorboard图的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！