how to plot real time line graph from dbn classifier train

Question

I'm working on a face recognition system using the DBN algorithm. when training data, the system will produce an error according to n-epoch. I want to make an error graph plot based on n-epoch

Training Code

    classifier = SupervisedDBNClassification (hidden_layers_structure=[200, 200],
    learning_rate_rbm=0.0001, 
    learning_rate=0.01,
    n_epochs_rbm=10,
    n_iter_backprop=100,
    batch_size=32,
    activation_function='relu',
    dropout_p = 0.2)

if we run that code, it will produce

    >> Epoch 84 finished    ANN training loss 0.681700
    >> Epoch 85 finished    ANN training loss 0.682314
    >> Epoch 86 finished    ANN training loss 0.680272
    >> Epoch 87 finished    ANN training loss 0.680542

so how i can plot it? This is the link where I got the code https://github.com/albertbup/deep-belief-network — iqbal putra, Jul 31 '19 at 03:12

score 0 · Answer 1 · answered Jul 31 '19 at 03:44

Use history = classifier.fit(x_train, y_train)

# list all data in history
print(history.history.keys())

You can access all the information like below to plot a line graph

history.history['acc'])
history.history['val_acc']
history.history['loss'])
history.history['val_loss']

For futher, look at this link

how to plot real time line graph from dbn classifier train

Training Code

if we run that code, it will produce

1 Answers1