如何实时可视化神经网络的训练？

Question

I am not using Pandas or PyTorch. I am using Keras and TensorFlow.

# Visualize training history
from keras.models import Sequential
from keras.layers import Dense
import matplotlib.pyplot as plt
import numpy
# load pima indians dataset
dataset = numpy.loadtxt("file.txt", 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, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, 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['accuracy'])
plt.plot(history.history['val_accuracy'])
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()

I found the above code somewhere on the Internet .

The problem with this code is, it doesn't show the training in real-time .

How can I achieve that in Keras?

Answer 1

I tested your code and implemented this , running the code in Jupiter shows exactly what you want the Realtime plotting graph of training and error loss, I checked outside the Jupiter the graph is not updated in Realtime may be there is some bug or may be it is only meant to be for Jupiter

# Visualize training history
from keras.models import Sequential
from keras.layers import Dense
import matplotlib.pyplot as plt
from livelossplot import PlotLossesKeras
import numpy
# load pima indians dataset
dataset = numpy.loadtxt("file.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, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, 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, callbacks=[PlotLossesKeras()])
# list all data in history
print(history.history.keys())
# summarize history for accuracy
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
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()