In [1]:

    

# %load /home/sjkim/.jupyter/head.py
%matplotlib inline
%load_ext autoreload
%autoreload 2
from importlib import reload

import matplotlib.pyplot as plt
import numpy as np

import pandas as pd
import os
#os.environ["CUDA_VISIBLE_DEVICES"]="0"

# seaborn
#import seaborn as sns
#sns.set( style = 'white', font_scale = 1.7)
#sns.set_style('ticks')
#plt.rcParams['savefig.dpi'] = 200

# font for matplotlib
#import matplotlib
#import matplotlib.font_manager as fm
#fm.get_fontconfig_fonts()
#font_location = '/usr/share/fonts/truetype/nanum/NanumGothicBold.ttf'
#font_name = fm.FontProperties(fname=font_location).get_name()
#matplotlib.rc('font', family=font_name)


    

In [2]:

    

import ex2_1_ann_mnist_cl
reload(ex2_1_ann_mnist_cl)


    

    
Out[2]:





<module 'ex2_1_ann_mnist_cl' from '/Users/james/Dropbox/Aspuru-Guzik/python_lab/py3/keraspp/tf2/ex2_1_ann_mnist_cl.py'>

In [3]:

    

ex2_1_ann_mnist_cl.main()


    

    




Train on 48000 samples, validate on 12000 samples
Epoch 1/15
48000/48000 [==============================] - 2s 36us/sample - loss: 0.3802 - accuracy: 0.8944 - val_loss: 0.2036 - val_accuracy: 0.9452
Epoch 2/15
48000/48000 [==============================] - 1s 26us/sample - loss: 0.1825 - accuracy: 0.9476 - val_loss: 0.1530 - val_accuracy: 0.9574
Epoch 3/15
48000/48000 [==============================] - 1s 26us/sample - loss: 0.1363 - accuracy: 0.9603 - val_loss: 0.1280 - val_accuracy: 0.9615
Epoch 4/15
48000/48000 [==============================] - 1s 25us/sample - loss: 0.1068 - accuracy: 0.9690 - val_loss: 0.1148 - val_accuracy: 0.9660
Epoch 5/15
48000/48000 [==============================] - 1s 26us/sample - loss: 0.0864 - accuracy: 0.9747 - val_loss: 0.1087 - val_accuracy: 0.9679
Epoch 6/15
48000/48000 [==============================] - 1s 25us/sample - loss: 0.0731 - accuracy: 0.9791 - val_loss: 0.0987 - val_accuracy: 0.9707
Epoch 7/15
48000/48000 [==============================] - 1s 26us/sample - loss: 0.0605 - accuracy: 0.9829 - val_loss: 0.0946 - val_accuracy: 0.9718
Epoch 8/15
48000/48000 [==============================] - 1s 25us/sample - loss: 0.0515 - accuracy: 0.9854 - val_loss: 0.0945 - val_accuracy: 0.9722
Epoch 9/15
48000/48000 [==============================] - 1s 26us/sample - loss: 0.0448 - accuracy: 0.9874 - val_loss: 0.0892 - val_accuracy: 0.9737
Epoch 10/15
48000/48000 [==============================] - 1s 26us/sample - loss: 0.0374 - accuracy: 0.9901 - val_loss: 0.0921 - val_accuracy: 0.9733
Epoch 11/15
48000/48000 [==============================] - 1s 25us/sample - loss: 0.0328 - accuracy: 0.9915 - val_loss: 0.0894 - val_accuracy: 0.9741
Epoch 12/15
48000/48000 [==============================] - 1s 26us/sample - loss: 0.0278 - accuracy: 0.9923 - val_loss: 0.0857 - val_accuracy: 0.9747
Epoch 13/15
48000/48000 [==============================] - 1s 26us/sample - loss: 0.0239 - accuracy: 0.9944 - val_loss: 0.0855 - val_accuracy: 0.9746
Epoch 14/15
48000/48000 [==============================] - 1s 25us/sample - loss: 0.0209 - accuracy: 0.9948 - val_loss: 0.0878 - val_accuracy: 0.9749
Epoch 15/15
48000/48000 [==============================] - 1s 26us/sample - loss: 0.0180 - accuracy: 0.9959 - val_loss: 0.0846 - val_accuracy: 0.9766
Test Loss and Accuracy -> [0.08365246526445844, 0.9736]






    













    




---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-3-a143c58d3171> in <module>
----> 1 ex2_1_ann_mnist_cl.main()

~/Dropbox/Aspuru-Guzik/python_lab/py3/keraspp/tf2/ex2_1_ann_mnist_cl.py in main()
    133     plot_loss(history)
    134     plt.show()
--> 135     plot_acc(history)
    136     plt.show()
    137 

~/Dropbox/Aspuru-Guzik/python_lab/py3/keraspp/tf2/ex2_1_ann_mnist_cl.py in plot_acc(history, title)
     85         history = history.history
     86 
---> 87     plt.plot(history['acc'])
     88     plt.plot(history['val_acc'])
     89     if title is not None:

KeyError: 'acc'