Real-time Keras + TensorFlow Card

Question

Inside the Jupyter laptop there is the following code:

# Visualize training history from keras.models import Sequential from keras.layers import Dense import matplotlib.pyplot as plt import numpy # fix random seed for reproducibility seed = 7 numpy.random.seed(seed) # load pima indians dataset dataset = numpy.loadtxt("pima-indians-diabetes.csv", delimiter=",") # split into input (X) and output (Y) variables X = dataset[:,0:8] Y = dataset[:,8] # create model model = Sequential() model.add(Dense(12, input_dim=8, kernel_initializer='uniform', activation='relu')) model.add(Dense(8, kernel_initializer='uniform', activation='relu')) model.add(Dense(1, kernel_initializer='uniform', activation='sigmoid')) # Compile model model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy']) # Fit the model history = model.fit(X, Y, validation_split=0.33, epochs=150, batch_size=10, verbose=0) # list all data in history print(history.history.keys()) # summarize history for accuracy plt.plot(history.history['acc']) plt.plot(history.history['val_acc']) plt.title('model accuracy') plt.ylabel('accuracy') plt.xlabel('epoch') plt.legend(['train', 'test'], loc='upper left') plt.show() # summarize history for loss plt.plot(history.history['loss']) plt.plot(history.history['val_loss']) plt.title('model loss') plt.ylabel('loss') plt.xlabel('epoch') plt.legend(['train', 'test'], loc='upper left') plt.show() 

The code collects history of eras and then displays the history of execution.

---

Q: How can I change the chart during training so that I can see the changes in real time?

Answer 1

Keras comes with a callback for TensorBoard .

You can easily add this behavior to your model, and then simply run the tensogram on top of the registration data.

 callbacks = [TensorBoard(log_dir='./logs')] result = model.fit(X, Y, ..., callbacks=callbacks) 

And then on your shell:

 tensorboard --logdir=/logs 

If you need it on your laptop, you can also write your own callback to get indicators during training:

  class LogCallback(Callback): def on_epoch_end(self, epoch, logs=None): print(logs["train_accuracy"]) 

This will ensure accuracy of training at the end of the current era and print it. There is good documentation on the keras official website.