Matplotlib kills jupyter kernel after training model

Question

I have run a neural network in a Jupyter notebook and I want to plot the results (loss vs. epoch number). I can run the model without problems, but then even a simple matplotlib plot kills the kernel.

Here is the code that creates the model and data I want to use:

from keras import models
from keras import layers
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline

from keras.datasets import imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data( num_words=10000)

# Change review into array
def vectorize_sequences(sequences, dimension=10000): 
    results = np.zeros((len(sequences), dimension)) # create all-zero matrix
    for i, sequence in enumerate(sequences):
        results[i, sequence] = 1. # If review has word, change that index to 1
    return results

x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)
y_train = np.asarray(train_labels).astype('float32') 
y_test = np.asarray(test_labels).astype('float32')

# Create model
model = models.Sequential()
model.add(layers.Dense(16, activation='relu', input_shape=(10000,))) # two int. layers w/16 hidden units each
model.add(layers.Dense(16, activation='relu')) 
model.add(layers.Dense(1, activation='sigmoid')) # outputs the scalar prediction
model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy'])

# Create mini-test data
x_val = x_train[:10000]
partial_x_train = x_train[10000:]
y_val = y_train[:10000]
partial_y_train = y_train[10000:]

# fit model
history = model.fit(partial_x_train, partial_y_train, epochs=20, batch_size=512, validation_data=(x_val, y_val))

# Get values for plot
history_dict = history.history
history_dict.keys()
loss_values = history_dict['loss'] 
val_loss_values = history_dict['val_loss']
epoch_num = [i for i in range(1,21)]

This works as expected. However, when I try to plot the data with the code below, I get a message: "The kernel appears to have died. It will restart automatically."

plt.plot(epoch_num, loss_values, 'bo', label='Training loss') 
plt.plot(epoch_num, val_loss_values, 'b', label='Validation loss')
plt.title('Training and validation loss') 
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()

I can restart the kernel and make matplotlib plots, but when I try to make a plot after running the model matplotlib causes the error to appear. I have tried updating keras, tensorflow, matplotlib, and numpy to no effect. Can anyone provide insight as to why this happens, and provide a solution?

Did you check your ram after training the model. How much it is left? I guess you are not haing enough memory to run matplotlib. Check mem stats using `htop`. — Pygirl, Apr 23 '20 at 01:48
The model uses 3.79GB of RAM. I have 64GB of ram on my computer. The model runs without a problem. I just can't use matplotlib afterwards. — pattidegner, Apr 23 '20 at 01:57

score 0 · Accepted Answer · answered Apr 26 '20 at 01:58

0

I used latest tensorflow and imported keras from tensorflow. Everything worked as expected. I changed first three line as shown below. Full code is here

from tensorflow import keras
from tensorflow.keras import models
from tensorflow.keras import layers

The following plot shows epoch versus loss

answered Apr 26 '20 at 01:58

Vishnuvardhan Janapati

3,088
1
16
25

I assumed that updating keras would also update tensorflow, but that is not the case. I checked my tensorflow version and realized it was old, updated it, and that fixed the problem. Thank you! – pattidegner Apr 26 '20 at 23:19

Matplotlib kills jupyter kernel after training model

1 Answers1