Keras load cell diagram structure

Question

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']) 

and call back the 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]) 

The output to the Tensorboard is as follows:

In other words, this is a complete mess.

• Is there anything I can do to make charting more structured?
• How to create bar graphs of scales using Keras and Tensorboard?

Answer 1

You can create a namespace to group layers in your model using K.name_scope('name_scope') .

Example:

 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) 

Thanks https://github.com/fchollet/keras/pull/4233#issuecomment-316954784