0

I'm currently working on a classification model built-up using TensorFlow framework applied with word embedding, LSTM layer, and Dense layer.

I wanted to see the performance of the training process; how much time Epoch took. So, instead of the boring figure(1), I want to plot a graph to show the training time and batch size like the figure(2). Does anyone know to archive that? I've been searching everywhere but none seems to work for me.

Figure(1)

enter image description here

Figure(2)

enter image description here

munirot
  • 97
  • 5
  • 16
  • 1
    Already answered in multiple ways: https://stackoverflow.com/questions/44746507/keras-tensorflow-realtime-training-chart – Ammar Tarajia Apr 05 '22 at 09:41
  • history = model.fit(x_train, y_train, epochs=1000, batch_size=5 ,validation_data=(x_test, y_test), callbacks=[custom_callback_5]) plt.plot(epoch_1_time, epoch_5_time) * plt.plot(epoch_1_time, epoch_10_time) plt.plot(epoch_1_time, epoch_50_time) plt.plot(epoch_1_time, epoch_100_time) plt.legend(["epoch_5_time", "epoch_10_time", "epoch_50_time", "epoch_100_time"]) plt.show() plt.close() – Jirayu Kaewprateep Apr 05 '22 at 11:47

0 Answers0